Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 247 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.7370. Min Act: -0.1700
Data Index: 2742844 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.5808. Min Act: -0.1700
Data Index: 5865549 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.5495. Min Act: -0.1700
Data Index: 7127188 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.5808. Min Act: -0.1700
Data Index: 8749389 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.5183. Min Act: -0.1700
Data Index: 644136 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.4870. Min Act: -0.1700
Data Index: 4618596 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.4558. Min Act: -0.1700
Data Index: 6535632 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.4870. Min Act: -0.1700
Data Index: 5149008 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.4870. Min Act: -0.1700
Data Index: 990667 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.4870. Min Act: -0.1700
Data Index: 8333631 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3933. Min Act: -0.1700
Data Index: 8444141 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3933. Min Act: -0.1700
Data Index: 742836 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3933. Min Act: -0.1700
Data Index: 4082607 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3620. Min Act: -0.1700
Data Index: 8736060 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3620. Min Act: -0.1700
Data Index: 3558460 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.2995. Min Act: -0.1700
Data Index: 4485376 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3308. Min Act: -0.1700
Data Index: 1066890 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.2995. Min Act: -0.1700
Data Index: 7331264 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3308. Min Act: -0.1700
Data Index: 830157 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7370. Min Range: -6.7370
Max Act: 6.3308. Min Act: -0.1700
Data Index: 5819532 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19