Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1566. Min Range: -6.1566
Max Act: 6.1566. Min Act: -0.1700
Data Index: 503753 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1566. Min Range: -6.1566
Max Act: 6.1254. Min Act: -0.1700
Data Index: 3415778 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.8754. Min Act: -0.1700
Data Index: 7228715 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.8441. Min Act: -0.1700
Data Index: 3297610 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.6879. Min Act: -0.1700
Data Index: 140061 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.6254. Min Act: -0.1700
Data Index: 3061232 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.6254. Min Act: -0.1700
Data Index: 1766354 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.6254. Min Act: -0.1700
Data Index: 7699331 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5941. Min Act: -0.1700
Data Index: 5069952 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5629. Min Act: -0.1700
Data Index: 375454 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5941. Min Act: -0.1700
Data Index: 548090 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5316. Min Act: -0.1700
Data Index: 1038614 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5316. Min Act: -0.1700
Data Index: 3503471 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5004. Min Act: -0.1700
Data Index: 7202334 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.5004. Min Act: -0.1700
Data Index: 112794 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.4379. Min Act: -0.1700
Data Index: 133690 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.4691. Min Act: -0.1700
Data Index: 4503241 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.4379. Min Act: -0.1700
Data Index: 8725470 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.4066. Min Act: -0.1700
Data Index: 317124 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1566. Min Range: -6.1566
Max Act: 5.3754. Min Act: -0.1700
Data Index: 2462520 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19