Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0675. Min Range: -8.0675
Max Act: 8.0675. Min Act: -0.1700
Data Index: 6411392 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0675. Min Range: -8.0675
Max Act: 8.0050. Min Act: -0.1700
Data Index: 6963197 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0675. Min Range: -8.0675
Max Act: 8.0050. Min Act: -0.1700
Data Index: 7273761 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.9425. Min Act: -0.1700
Data Index: 212196 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.8800. Min Act: -0.1700
Data Index: 4502961 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.8800. Min Act: -0.1700
Data Index: 5185921 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.8175. Min Act: -0.1700
Data Index: 7257172 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.8175. Min Act: -0.1700
Data Index: 4486538 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.8175. Min Act: -0.1700
Data Index: 2913403 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.7550. Min Act: -0.1700
Data Index: 1105372 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.7550. Min Act: -0.1700
Data Index: 8463084 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6925. Min Act: -0.1700
Data Index: 3760873 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6925. Min Act: -0.1700
Data Index: 6750784 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6925. Min Act: -0.1700
Data Index: 1603091 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 3557463 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 1968462 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 7718331 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 3735950 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 2595170 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0675. Min Range: -8.0675
Max Act: 7.6300. Min Act: -0.1700
Data Index: 3856395 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19