Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 367 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0729. Min Act: -0.1700
Data Index: 3300505 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0416. Min Act: -0.1700
Data Index: 3944016 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0103. Min Act: -0.1700
Data Index: 6780489 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0103. Min Act: -0.1700
Data Index: 5046499 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 1682626 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 1774037 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 259202 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 3944028 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 8129624 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 3080372 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5760887 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 1437271 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0103. Min Act: -0.1700
Data Index: 5163471 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 1168626 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5163470 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5163480 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9478. Min Act: -0.1700
Data Index: 516525 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9165. Min Act: -0.1700
Data Index: 5433269 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9791. Min Act: -0.1700
Data Index: 637465 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9478. Min Act: -0.1700
Data Index: 4761236 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19