Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.4972. Min Act: -0.1700
Data Index: 880039 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.2785. Min Act: -0.1700
Data Index: 6135175 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.3097. Min Act: -0.1700
Data Index: 904609 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.2160. Min Act: -0.1700
Data Index: 1995464 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.2160. Min Act: -0.1700
Data Index: 3245111 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.1535. Min Act: -0.1700
Data Index: 8098001 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8201981 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0910. Min Act: -0.1700
Data Index: 5575950 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.1222. Min Act: -0.1700
Data Index: 5969419 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.1222. Min Act: -0.1700
Data Index: 3539436 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0597. Min Act: -0.1700
Data Index: 3463396 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0910. Min Act: -0.1700
Data Index: 5385853 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0910. Min Act: -0.1700
Data Index: 2481750 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.1222. Min Act: -0.1700
Data Index: 326443 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0597. Min Act: -0.1700
Data Index: 5385857 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0285. Min Act: -0.1700
Data Index: 576066 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0597. Min Act: -0.1700
Data Index: 375703 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0285. Min Act: -0.1700
Data Index: 5013600 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0597. Min Act: -0.1700
Data Index: 6919078 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4972. Min Range: -5.4972
Max Act: 5.0597. Min Act: -0.1700
Data Index: 6958725 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19