Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4904 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.9432. Min Act: -0.1700
Data Index: 812162 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.7869. Min Act: -0.1700
Data Index: 1492951 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.7869. Min Act: -0.1700
Data Index: 3457216 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.7557. Min Act: -0.1700
Data Index: 1831402 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.7244. Min Act: -0.1700
Data Index: 8563004 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4170972 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4868036 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 4000761 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 8131929 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 5597137 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6464649 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.7244. Min Act: -0.1700
Data Index: 1953554 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 5654010 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 4338209 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 3836424 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 6760932 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6932. Min Act: -0.1700
Data Index: 5095504 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4342831 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6307. Min Act: -0.1700
Data Index: 1379731 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9432. Min Range: -5.9432
Max Act: 5.6619. Min Act: -0.1700
Data Index: 2776598 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19