Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.8118. Min Act: -0.1700
Data Index: 2049916 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.4993. Min Act: -0.1700
Data Index: 854079 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.3743. Min Act: -0.1700
Data Index: 7578618 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.2493. Min Act: -0.1700
Data Index: 5772100 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.1868. Min Act: -0.1700
Data Index: 854080 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.1243. Min Act: -0.1700
Data Index: 4839956 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.1243. Min Act: -0.1700
Data Index: 1420234 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.8118. Min Range: -14.8118
Max Act: 14.0618. Min Act: -0.1700
Data Index: 8339520 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.9993. Min Act: -0.1700
Data Index: 8087382 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.9368. Min Act: -0.1700
Data Index: 5091955 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.9368. Min Act: -0.1699
Data Index: 6306990 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.8743. Min Act: -0.1700
Data Index: 5373227 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.8743. Min Act: -0.1700
Data Index: 5181209 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.8118. Min Act: -0.1700
Data Index: 5099461 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.8118. Min Act: -0.1700
Data Index: 2492999 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.7493. Min Act: -0.1700
Data Index: 3684075 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.8118. Min Act: -0.1700
Data Index: 2454038 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.7493. Min Act: -0.1700
Data Index: 1452986 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.6868. Min Act: -0.1700
Data Index: 6420606 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.8118. Min Range: -14.8118
Max Act: 13.6868. Min Act: -0.1700
Data Index: 3345968 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19