Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.9419. Min Act: -0.1700
Data Index: 217080 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3164517 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.5982. Min Act: -0.1700
Data Index: 4313214 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.5982. Min Act: -0.1700
Data Index: 7222941 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.5044. Min Act: -0.1700
Data Index: 5732568 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.5044. Min Act: -0.1700
Data Index: 2434270 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.5044. Min Act: -0.1700
Data Index: 4457656 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4419. Min Act: -0.1700
Data Index: 6777504 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4419. Min Act: -0.1700
Data Index: 7062486 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4419. Min Act: -0.1700
Data Index: 1365760 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 8375765 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 2257650 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 2118044 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4632246 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 2555978 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4556447 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 995460 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4195803 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.3794. Min Act: -0.1700
Data Index: 2153139 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9419. Min Range: -6.9419
Max Act: 6.3794. Min Act: -0.1700
Data Index: 7565469 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19