Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1254 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4111. Min Range: -7.4111
Max Act: 7.4111. Min Act: -0.1700
Data Index: 3160739 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4111. Min Range: -7.4111
Max Act: 7.1611. Min Act: -0.1700
Data Index: 8095933 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4111. Min Range: -7.4111
Max Act: 7.0048. Min Act: -0.1700
Data Index: 1790514 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4111. Min Range: -7.4111
Max Act: 7.0361. Min Act: -0.1700
Data Index: 1685504 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.9736. Min Act: -0.1700
Data Index: 949325 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.8486. Min Act: -0.1700
Data Index: 4408105 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.8486. Min Act: -0.1700
Data Index: 7111627 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7861. Min Act: -0.1700
Data Index: 5407142 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.8173. Min Act: -0.1700
Data Index: 7331164 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.8173. Min Act: -0.1700
Data Index: 2813112 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7861. Min Act: -0.1700
Data Index: 4509347 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7861. Min Act: -0.1700
Data Index: 5852011 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7861. Min Act: -0.1700
Data Index: 3682213 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7548. Min Act: -0.1700
Data Index: 6771169 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7548. Min Act: -0.1700
Data Index: 7847652 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7236. Min Act: -0.1700
Data Index: 3875657 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7236. Min Act: -0.1700
Data Index: 5230938 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7236. Min Act: -0.1700
Data Index: 3593011 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7236. Min Act: -0.1700
Data Index: 4550161 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4111. Min Range: -7.4111
Max Act: 6.7236. Min Act: -0.1700
Data Index: 1453574 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19