Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.9840. Min Act: -0.1700
Data Index: 8506894 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.9215. Min Act: -0.1700
Data Index: 1002389 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.8278. Min Act: -0.1700
Data Index: 2660972 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7471045 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7965. Min Act: -0.1700
Data Index: 2545942 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7049272 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7965. Min Act: -0.1700
Data Index: 2660974 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7965. Min Act: -0.1700
Data Index: 6293752 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7653. Min Act: -0.1700
Data Index: 506944 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7653. Min Act: -0.1700
Data Index: 216733 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7653. Min Act: -0.1700
Data Index: 8469492 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7653. Min Act: -0.1700
Data Index: 2660973 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7340. Min Act: -0.1700
Data Index: 8039830 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7028. Min Act: -0.1700
Data Index: 265790 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7028. Min Act: -0.1700
Data Index: 8676308 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7028. Min Act: -0.1700
Data Index: 3941807 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7028. Min Act: -0.1700
Data Index: 3320994 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7522486 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.6715. Min Act: -0.1700
Data Index: 6005991 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9840. Min Range: -5.9840
Max Act: 5.6715. Min Act: -0.1700
Data Index: 2982862 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19