Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2302. Min Range: -8.2302
Max Act: 8.2302. Min Act: -0.1700
Data Index: 7303570 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2302. Min Range: -8.2302
Max Act: 8.0427. Min Act: -0.1700
Data Index: 5721215 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.8865. Min Act: -0.1700
Data Index: 4685945 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.8240. Min Act: -0.1700
Data Index: 3589090 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.7927. Min Act: -0.1700
Data Index: 4446953 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.7615. Min Act: -0.1700
Data Index: 1682545 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.7302. Min Act: -0.1700
Data Index: 6977661 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.7302. Min Act: -0.1700
Data Index: 4741739 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.7302. Min Act: -0.1700
Data Index: 3305950 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6677. Min Act: -0.1700
Data Index: 5593144 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6677. Min Act: -0.1700
Data Index: 303541 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6677. Min Act: -0.1700
Data Index: 4997566 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.5740. Min Act: -0.1700
Data Index: 4222519 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6052. Min Act: -0.1700
Data Index: 3260894 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6052. Min Act: -0.1700
Data Index: 6123740 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6052. Min Act: -0.1700
Data Index: 6242771 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.6052. Min Act: -0.1700
Data Index: 4554762 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.5740. Min Act: -0.1700
Data Index: 4519299 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.5740. Min Act: -0.1700
Data Index: 4357887 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2302. Min Range: -8.2302
Max Act: 7.5740. Min Act: -0.1700
Data Index: 950146 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19