Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4328. Min Range: -6.4328
Max Act: 6.4328. Min Act: -0.1700
Data Index: 6869222 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7765. Min Act: -0.1700
Data Index: 5890639 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 4122101 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7765. Min Act: -0.1700
Data Index: 8054227 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7140. Min Act: -0.1700
Data Index: 8655232 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 2694298 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 7601310 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6515. Min Act: -0.1700
Data Index: 4991536 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 8604025 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 4304401 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5890. Min Act: -0.1700
Data Index: 3683661 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 7844380 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 3349264 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 3876749 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 6793032 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 4995845 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 8562479 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 8075198 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.4953. Min Act: -0.1700
Data Index: 8765224 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.4953. Min Act: -0.1700
Data Index: 5077473 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19