Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.3430. Min Act: -0.1700
Data Index: 3081511 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.3430. Min Act: -0.1700
Data Index: 8218599 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.3430. Min Act: -0.1700
Data Index: 2480799 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.2492. Min Act: -0.1700
Data Index: 5564560 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.1867. Min Act: -0.1700
Data Index: 4361025 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.2180. Min Act: -0.1700
Data Index: 3271317 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.1867. Min Act: -0.1700
Data Index: 8366471 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.2180. Min Act: -0.1700
Data Index: 5974737 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.1555. Min Act: -0.1700
Data Index: 2650001 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5426854 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.1867. Min Act: -0.1700
Data Index: 2688294 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0930. Min Act: -0.1700
Data Index: 2865583 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0617. Min Act: -0.1700
Data Index: 735377 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0930. Min Act: -0.1700
Data Index: 3170580 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0617. Min Act: -0.1700
Data Index: 6213329 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0617. Min Act: -0.1700
Data Index: 8142350 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0305. Min Act: -0.1700
Data Index: 6245089 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0930. Min Act: -0.1700
Data Index: 6541244 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3430. Min Range: -5.3430
Max Act: 4.9992. Min Act: -0.1700
Data Index: 8166123 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3430. Min Range: -5.3430
Max Act: 5.0305. Min Act: -0.1700
Data Index: 6505150 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19