Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2314 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.9082. Min Act: -0.1700
Data Index: 8135269 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.8143. Min Act: -0.1700
Data Index: 4092682 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.8143. Min Act: -0.1700
Data Index: 4965718 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.7518. Min Act: -0.1700
Data Index: 8579498 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.7674. Min Act: -0.1700
Data Index: 6526059 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.7518. Min Act: -0.1700
Data Index: 3604804 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.7205. Min Act: -0.1700
Data Index: 2455101 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.7518. Min Act: -0.1700
Data Index: 8101688 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6579. Min Act: -0.1700
Data Index: 5480283 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6579. Min Act: -0.1700
Data Index: 3490882 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6423. Min Act: -0.1700
Data Index: 6391778 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6423. Min Act: -0.1700
Data Index: 8458995 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6423. Min Act: -0.1700
Data Index: 442234 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6423. Min Act: -0.1700
Data Index: 4124158 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6266. Min Act: -0.1700
Data Index: 5829896 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.6423. Min Act: -0.1700
Data Index: 5504083 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.5953. Min Act: -0.1700
Data Index: 8073136 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.5953. Min Act: -0.1700
Data Index: 2474737 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.5953. Min Act: -0.1700
Data Index: 5650460 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9082. Min Range: -3.9082
Max Act: 3.5797. Min Act: -0.1700
Data Index: 6166713 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19