Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.9003. Min Act: -0.1700
Data Index: 1896620 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5878. Min Act: -0.1700
Data Index: 1487995 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5565. Min Act: -0.1700
Data Index: 4490686 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5253. Min Act: -0.1700
Data Index: 954150 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5253. Min Act: -0.1700
Data Index: 5156647 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5253. Min Act: -0.1700
Data Index: 1344179 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.5253. Min Act: -0.1700
Data Index: 4490682 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4940. Min Act: -0.1700
Data Index: 5423803 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4940. Min Act: -0.1700
Data Index: 1344177 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4940. Min Act: -0.1700
Data Index: 40229 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4940. Min Act: -0.1700
Data Index: 5054373 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4627. Min Act: -0.1700
Data Index: 1344178 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4940. Min Act: -0.1700
Data Index: 2720 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4627. Min Act: -0.1700
Data Index: 3408729 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4315. Min Act: -0.1700
Data Index: 7468273 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4315. Min Act: -0.1700
Data Index: 4528006 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4315. Min Act: -0.1700
Data Index: 2529506 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4002. Min Act: -0.1700
Data Index: 3420036 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4315. Min Act: -0.1700
Data Index: 1344182 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9003. Min Range: -4.9003
Max Act: 4.4002. Min Act: -0.1700
Data Index: 4490687 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19