Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.7201. Min Act: -0.1699
Data Index: 4552772 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.3451. Min Act: -0.1700
Data Index: 7045209 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.2826. Min Act: -0.1700
Data Index: 2554101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.2826. Min Act: -0.1700
Data Index: 2267328 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.2201. Min Act: -0.1700
Data Index: 1018892 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.2201. Min Act: -0.1700
Data Index: 6763203 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.2201. Min Act: -0.1700
Data Index: 4276914 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1888. Min Act: -0.1700
Data Index: 5992685 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1888. Min Act: -0.1700
Data Index: 2855419 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1576. Min Act: -0.1700
Data Index: 4552761 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1576. Min Act: -0.1700
Data Index: 4305578 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1263. Min Act: -0.1700
Data Index: 4248094 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.1263. Min Act: -0.1700
Data Index: 1117325 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0638. Min Act: -0.1700
Data Index: 6326911 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 7694249 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 2595538 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0326. Min Act: -0.1700
Data Index: 1905593 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0013. Min Act: -0.1700
Data Index: 3520154 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7201. Min Range: -5.7201
Max Act: 5.0013. Min Act: -0.1700
Data Index: 1274992 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7201. Min Range: -5.7201
Max Act: 4.9701. Min Act: -0.1700
Data Index: 182715 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19