Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2233. Min Range: -6.2233
Max Act: 6.2233. Min Act: -0.1700
Data Index: 3594949 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.9733. Min Act: -0.1700
Data Index: 7020404 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.8171. Min Act: -0.1700
Data Index: 7534112 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7858. Min Act: -0.1700
Data Index: 478685 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7858. Min Act: -0.1700
Data Index: 7845401 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7546. Min Act: -0.1700
Data Index: 6867104 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7233. Min Act: -0.1700
Data Index: 3111623 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7233. Min Act: -0.1700
Data Index: 3013832 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7233. Min Act: -0.1700
Data Index: 6524363 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7546. Min Act: -0.1700
Data Index: 4916214 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.7233. Min Act: -0.1700
Data Index: 5497529 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 2672914 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 3561077 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 593066 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 2772054 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 2613653 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 6031406 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6921. Min Act: -0.1700
Data Index: 3032677 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6296. Min Act: -0.1700
Data Index: 325914 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2233. Min Range: -6.2233
Max Act: 5.6296. Min Act: -0.1700
Data Index: 2032572 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19