Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.2171. Min Act: -0.1700
Data Index: 5895540 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1234. Min Act: -0.1700
Data Index: 792242 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.1234. Min Act: -0.1700
Data Index: 2665703 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2171. Min Range: -4.2171
Max Act: 4.0921. Min Act: -0.1700
Data Index: 1509870 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9983. Min Act: -0.1700
Data Index: 2517476 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9983. Min Act: -0.1700
Data Index: 8082163 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9358. Min Act: -0.1700
Data Index: 5805380 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9358. Min Act: -0.1700
Data Index: 3209660 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9358. Min Act: -0.1700
Data Index: 4742100 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9045. Min Act: -0.1700
Data Index: 1187881 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.9045. Min Act: -0.1700
Data Index: 583980 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.8733. Min Act: -0.1700
Data Index: 7601039 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.8420. Min Act: -0.1700
Data Index: 1116454 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.8420. Min Act: -0.1700
Data Index: 8102284 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7951. Min Act: -0.1700
Data Index: 590159 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7795. Min Act: -0.1700
Data Index: 6575539 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7951. Min Act: -0.1700
Data Index: 6975929 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7951. Min Act: -0.1700
Data Index: 5968337 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7795. Min Act: -0.1700
Data Index: 824314 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2171. Min Range: -4.2171
Max Act: 3.7795. Min Act: -0.1700
Data Index: 7760274 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19