Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2230. Min Range: -8.2230
Max Act: 8.2230. Min Act: -0.1700
Data Index: 1224023 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2230. Min Range: -8.2230
Max Act: 8.0355. Min Act: -0.1700
Data Index: 7256700 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2230. Min Range: -8.2230
Max Act: 8.0355. Min Act: -0.1700
Data Index: 6254943 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2230. Min Range: -8.2230
Max Act: 8.0355. Min Act: -0.1700
Data Index: 7126 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.9730. Min Act: -0.1700
Data Index: 4628274 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.9105. Min Act: -0.1700
Data Index: 2471353 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.9105. Min Act: -0.1700
Data Index: 414337 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.9105. Min Act: -0.1700
Data Index: 2792765 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.8480. Min Act: -0.1700
Data Index: 6004683 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 6919431 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 7518101 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 7047805 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 330966 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 2828076 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 5566546 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7230. Min Act: -0.1700
Data Index: 2215213 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7855. Min Act: -0.1700
Data Index: 7857942 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7230. Min Act: -0.1700
Data Index: 5907274 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7230. Min Act: -0.1700
Data Index: 4272658 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2230. Min Range: -8.2230
Max Act: 7.7230. Min Act: -0.1700
Data Index: 5540432 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19