Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.4513. Min Range: -16.4513
Max Act: 16.4513. Min Act: -0.1700
Data Index: 4760908 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.9513. Min Act: -0.1700
Data Index: 6321946 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.8263. Min Act: -0.1700
Data Index: 7457522 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.8263. Min Act: -0.1700
Data Index: 5018833 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.8263. Min Act: -0.1700
Data Index: 2034991 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.8263. Min Act: -0.1700
Data Index: 4263849 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.7013. Min Act: -0.1700
Data Index: 5832176 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.7013. Min Act: -0.1700
Data Index: 970252 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.7013. Min Act: -0.1700
Data Index: 3081421 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.7013. Min Act: -0.1700
Data Index: 5503854 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5763. Min Act: -0.1700
Data Index: 712907 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5763. Min Act: -0.1700
Data Index: 7060749 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5763. Min Act: -0.1700
Data Index: 8012162 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5763. Min Act: -0.1700
Data Index: 4233674 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5138. Min Act: -0.1700
Data Index: 8068443 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5138. Min Act: -0.1700
Data Index: 7200771 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.4513. Min Act: -0.1700
Data Index: 4075828 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.5138. Min Act: -0.1700
Data Index: 5801789 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.3888. Min Act: -0.1700
Data Index: 5551182 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.4513. Min Range: -16.4513
Max Act: 15.3888. Min Act: -0.1700
Data Index: 4069586 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19