Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4668. Min Act: -0.1700
Data Index: 7949974 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4375. Min Act: -0.1700
Data Index: 2892020 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4330. Min Act: -0.1700
Data Index: 6225804 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4240. Min Act: -0.1700
Data Index: 7869929 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4204. Min Act: -0.1700
Data Index: 2619164 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4195. Min Act: -0.1700
Data Index: 8718309 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.4222. Min Act: -0.1700
Data Index: 3962367 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3824. Min Act: -0.1700
Data Index: 4339685 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3973. Min Act: -0.1700
Data Index: 5580325 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3777. Min Act: -0.1700
Data Index: 964291 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3838. Min Act: -0.1700
Data Index: 5145617 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3816. Min Act: -0.1700
Data Index: 1254585 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3694. Min Act: -0.1700
Data Index: 446487 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3720. Min Act: -0.1700
Data Index: 4543223 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3673. Min Act: -0.1700
Data Index: 749627 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3643. Min Act: -0.1700
Data Index: 3408312 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3638. Min Act: -0.1700
Data Index: 7195263 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3570. Min Act: -0.1700
Data Index: 8385329 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3561. Min Act: -0.1700
Data Index: 2912806 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4668. Min Range: -0.4668
Max Act: 0.3506. Min Act: -0.1700
Data Index: 534180 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19