Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0197. Min Range: -8.0197
Max Act: 8.0197. Min Act: -0.1700
Data Index: 5819487 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0197. Min Range: -8.0197
Max Act: 8.0197. Min Act: -0.1700
Data Index: 4364447 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.9572. Min Act: -0.1700
Data Index: 1600245 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.9572. Min Act: -0.1700
Data Index: 8399532 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8947. Min Act: -0.1700
Data Index: 2397881 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 8149020 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 7029046 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 7025561 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 8787691 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 50934 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 3700153 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 1437214 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5577657 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 474914 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.7697. Min Act: -0.1700
Data Index: 4007758 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5965750 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.7072. Min Act: -0.1700
Data Index: 4237403 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.7072. Min Act: -0.1700
Data Index: 1190013 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.7072. Min Act: -0.1700
Data Index: 6201558 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0197. Min Range: -8.0197
Max Act: 7.6447. Min Act: -0.1700
Data Index: 7292639 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19