Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1192. Min Range: -8.1192
Max Act: 8.1192. Min Act: -0.1700
Data Index: 1758089 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.7129. Min Act: -0.1700
Data Index: 6203915 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.6817. Min Act: -0.1700
Data Index: 2030953 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.6817. Min Act: -0.1700
Data Index: 5430630 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.6504. Min Act: -0.1700
Data Index: 2481464 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4942. Min Act: -0.1700
Data Index: 675721 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4317. Min Act: -0.1700
Data Index: 4858312 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4004. Min Act: -0.1700
Data Index: 3764128 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4317. Min Act: -0.1700
Data Index: 5935066 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4004. Min Act: -0.1700
Data Index: 2548883 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.4004. Min Act: -0.1700
Data Index: 6824197 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3379. Min Act: -0.1700
Data Index: 3676873 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3379. Min Act: -0.1700
Data Index: 495355 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3379. Min Act: -0.1700
Data Index: 6086234 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3379. Min Act: -0.1700
Data Index: 1178151 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3067. Min Act: -0.1700
Data Index: 5643800 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3067. Min Act: -0.1700
Data Index: 6327067 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.3067. Min Act: -0.1700
Data Index: 8174931 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.2754. Min Act: -0.1700
Data Index: 3569828 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1192. Min Range: -8.1192
Max Act: 7.2754. Min Act: -0.1700
Data Index: 700778 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19