Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.6305. Min Act: -0.1700
Data Index: 2633034 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.5680. Min Act: -0.1700
Data Index: 3731378 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.3805. Min Act: -0.1700
Data Index: 6799030 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.3805. Min Act: -0.1700
Data Index: 3157889 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.2555. Min Act: -0.1700
Data Index: 3315453 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.2555. Min Act: -0.1700
Data Index: 1515818 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.1930. Min Act: -0.1700
Data Index: 4662463 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.0680. Min Act: -0.1700
Data Index: 6517872 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.1930. Min Act: -0.1700
Data Index: 4259702 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.0680. Min Act: -0.1700
Data Index: 4755628 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6305. Min Range: -9.6305
Max Act: 9.0055. Min Act: -0.1700
Data Index: 5173065 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.8805. Min Act: -0.1700
Data Index: 5165487 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.8180. Min Act: -0.1700
Data Index: 3037041 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.8180. Min Act: -0.1700
Data Index: 2537001 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.8180. Min Act: -0.1700
Data Index: 2610933 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.7555. Min Act: -0.1700
Data Index: 716240 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.7555. Min Act: -0.1700
Data Index: 2775695 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.7555. Min Act: -0.1700
Data Index: 4189761 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.6930. Min Act: -0.1700
Data Index: 3384925 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6305. Min Range: -9.6305
Max Act: 8.7555. Min Act: -0.1700
Data Index: 2029343 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19