Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.9050. Min Act: -0.1700
Data Index: 8246627 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8738. Min Act: -0.1700
Data Index: 4183028 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8738. Min Act: -0.1700
Data Index: 7968347 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8425. Min Act: -0.1700
Data Index: 2661440 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.8113. Min Act: -0.1700
Data Index: 3917443 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6863. Min Act: -0.1700
Data Index: 2879757 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6863. Min Act: -0.1700
Data Index: 8472255 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6863. Min Act: -0.1700
Data Index: 2916247 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6863. Min Act: -0.1700
Data Index: 4958627 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6238. Min Act: -0.1700
Data Index: 649704 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6238. Min Act: -0.1700
Data Index: 8720166 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.6238. Min Act: -0.1700
Data Index: 2510360 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5925. Min Act: -0.1700
Data Index: 99599 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5925. Min Act: -0.1700
Data Index: 5876419 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5613. Min Act: -0.1700
Data Index: 8436000 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5925. Min Act: -0.1700
Data Index: 2491001 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5300. Min Act: -0.1700
Data Index: 5849511 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1458967 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5300. Min Act: -0.1700
Data Index: 3035138 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9050. Min Range: -4.9050
Max Act: 4.5300. Min Act: -0.1700
Data Index: 4037949 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19