Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5696 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.6476. Min Act: -0.1700
Data Index: 3825372 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.6476. Min Act: -0.1700
Data Index: 7824659 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.6163. Min Act: -0.1700
Data Index: 7004345 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5851. Min Act: -0.1700
Data Index: 6492156 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 7443020 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5226. Min Act: -0.1700
Data Index: 5659139 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 4344285 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 1531118 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5226. Min Act: -0.1700
Data Index: 3608975 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5226. Min Act: -0.1700
Data Index: 7443019 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 2348561 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.5226. Min Act: -0.1700
Data Index: 7846287 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 1607655 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4913. Min Act: -0.1700
Data Index: 3190869 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4913. Min Act: -0.1700
Data Index: 2458930 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4913. Min Act: -0.1700
Data Index: 7827984 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 2499148 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 7689069 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 4545864 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6476. Min Range: -5.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 5906540 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19