Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3241. Min Range: -6.3241
Max Act: 6.3241. Min Act: -0.1700
Data Index: 1997949 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3241. Min Range: -6.3241
Max Act: 6.2928. Min Act: -0.1700
Data Index: 6440425 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3241. Min Range: -6.3241
Max Act: 6.2616. Min Act: -0.1700
Data Index: 2539146 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3241. Min Range: -6.3241
Max Act: 6.1053. Min Act: -0.1700
Data Index: 4375407 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3241. Min Range: -6.3241
Max Act: 6.0116. Min Act: -0.1700
Data Index: 4242583 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3378232 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.9491. Min Act: -0.1700
Data Index: 1997950 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.9178. Min Act: -0.1700
Data Index: 8149820 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.8866. Min Act: -0.1700
Data Index: 7160394 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.8553. Min Act: -0.1700
Data Index: 8617190 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7928. Min Act: -0.1700
Data Index: 1611539 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7928. Min Act: -0.1700
Data Index: 4623552 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7616. Min Act: -0.1700
Data Index: 3194529 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7616. Min Act: -0.1700
Data Index: 7240192 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7303. Min Act: -0.1700
Data Index: 2455680 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.7303. Min Act: -0.1700
Data Index: 4272823 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.6991. Min Act: -0.1700
Data Index: 6184786 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.6991. Min Act: -0.1700
Data Index: 5766884 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.6991. Min Act: -0.1700
Data Index: 2209205 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3241. Min Range: -6.3241
Max Act: 5.6678. Min Act: -0.1700
Data Index: 6499155 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19