Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.6512. Min Act: -0.1700
Data Index: 6645814 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.2762. Min Act: -0.1700
Data Index: 4200160 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.2449. Min Act: -0.1700
Data Index: 3205900 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.1199. Min Act: -0.1700
Data Index: 4511681 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.0262. Min Act: -0.1700
Data Index: 5017051 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.0262. Min Act: -0.1700
Data Index: 34282 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.0262. Min Act: -0.1700
Data Index: 884721 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.9949. Min Act: -0.1700
Data Index: 2399486 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6512. Min Range: -8.6512
Max Act: 8.0262. Min Act: -0.1700
Data Index: 2533499 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.9637. Min Act: -0.1700
Data Index: 6635986 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.9637. Min Act: -0.1700
Data Index: 4378305 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.9012. Min Act: -0.1700
Data Index: 7896178 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.8699. Min Act: -0.1700
Data Index: 4491358 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.8074. Min Act: -0.1700
Data Index: 1776430 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7762. Min Act: -0.1700
Data Index: 5682923 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7762. Min Act: -0.1700
Data Index: 2667923 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7762. Min Act: -0.1700
Data Index: 4223220 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7762. Min Act: -0.1700
Data Index: 6289598 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7449. Min Act: -0.1700
Data Index: 988986 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6512. Min Range: -8.6512
Max Act: 7.7449. Min Act: -0.1700
Data Index: 239724 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19