Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.4974. Min Act: -0.1700
Data Index: 6496995 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6366086 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.3411. Min Act: -0.1700
Data Index: 4464799 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.2786. Min Act: -0.1700
Data Index: 445402 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 6735316 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.2161. Min Act: -0.1700
Data Index: 5422441 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.1849. Min Act: -0.1700
Data Index: 8168274 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.1536. Min Act: -0.1700
Data Index: 5788186 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.1536. Min Act: -0.1700
Data Index: 3870654 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.0911. Min Act: -0.1700
Data Index: 50903 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.0599. Min Act: -0.1700
Data Index: 7738088 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.0286. Min Act: -0.1700
Data Index: 631226 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.0286. Min Act: -0.1700
Data Index: 3180601 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4974. Min Range: -5.4974
Max Act: 5.0286. Min Act: -0.1700
Data Index: 8787966 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9974. Min Act: -0.1700
Data Index: 4940611 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9974. Min Act: -0.1700
Data Index: 8254217 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9661. Min Act: -0.1700
Data Index: 8044704 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9661. Min Act: -0.1700
Data Index: 5068462 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9661. Min Act: -0.1700
Data Index: 2834376 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4974. Min Range: -5.4974
Max Act: 4.9349. Min Act: -0.1700
Data Index: 5549209 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19