Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1075. Min Range: -6.1075
Max Act: 6.1075. Min Act: -0.1700
Data Index: 6827687 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.8575. Min Act: -0.1700
Data Index: 619379 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.8262. Min Act: -0.1700
Data Index: 7065074 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.8262. Min Act: -0.1700
Data Index: 8591441 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1282461 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.7325. Min Act: -0.1700
Data Index: 3632227 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.7012. Min Act: -0.1700
Data Index: 6709049 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.7012. Min Act: -0.1700
Data Index: 1502096 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6387. Min Act: -0.1700
Data Index: 3894792 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.7012. Min Act: -0.1700
Data Index: 3434360 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 8421038 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 7203319 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 8718940 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6387. Min Act: -0.1700
Data Index: 5347090 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6387. Min Act: -0.1700
Data Index: 52292 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 8202110 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 3434363 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.5762. Min Act: -0.1700
Data Index: 8632633 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 3316176 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1075. Min Range: -6.1075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 633971 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19