Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0117. Min Range: -7.0117
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3420353 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.9180. Min Act: -0.1700
Data Index: 8359526 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.9180. Min Act: -0.1700
Data Index: 1641472 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.6055. Min Act: -0.1700
Data Index: 4568861 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.5117. Min Act: -0.1700
Data Index: 6110016 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.4805. Min Act: -0.1700
Data Index: 1322278 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.4492. Min Act: -0.1700
Data Index: 4814707 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.4492. Min Act: -0.1700
Data Index: 8012454 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.4492. Min Act: -0.1700
Data Index: 6144400 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.4492. Min Act: -0.1700
Data Index: 6144361 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.3555. Min Act: -0.1700
Data Index: 6549469 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.3555. Min Act: -0.1700
Data Index: 1289693 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.3242. Min Act: -0.1700
Data Index: 5867008 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.3242. Min Act: -0.1700
Data Index: 8257618 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.2930. Min Act: -0.1700
Data Index: 4925681 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.2617. Min Act: -0.1700
Data Index: 7278033 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.1992. Min Act: -0.1700
Data Index: 5746129 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.2617. Min Act: -0.1700
Data Index: 7278020 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.1992. Min Act: -0.1700
Data Index: 3019197 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0117. Min Range: -7.0117
Max Act: 6.2305. Min Act: -0.1700
Data Index: 2928120 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19