Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4470 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.9106. Min Act: -0.1700
Data Index: 4625502 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.7698. Min Act: -0.1700
Data Index: 1829661 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.7229. Min Act: -0.1700
Data Index: 7732919 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.7229. Min Act: -0.1700
Data Index: 6593655 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.6916. Min Act: -0.1700
Data Index: 2605591 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.6603. Min Act: -0.1700
Data Index: 2358633 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.6291. Min Act: -0.1700
Data Index: 8680974 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.6291. Min Act: -0.1700
Data Index: 8804594 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5821. Min Act: -0.1700
Data Index: 5791728 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5821. Min Act: -0.1700
Data Index: 6400173 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5978. Min Act: -0.1700
Data Index: 2055615 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5664. Min Act: -0.1700
Data Index: 6694395 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5978. Min Act: -0.1700
Data Index: 5488871 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5821. Min Act: -0.1700
Data Index: 2846861 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5821. Min Act: -0.1700
Data Index: 884106 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5664. Min Act: -0.1700
Data Index: 1279854 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5508. Min Act: -0.1700
Data Index: 8717298 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5664. Min Act: -0.1700
Data Index: 8598541 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5508. Min Act: -0.1700
Data Index: 6252824 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9106. Min Range: -3.9106
Max Act: 3.5508. Min Act: -0.1700
Data Index: 5681213 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19