Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.9686. Min Act: -0.1700
Data Index: 1207283 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.9686. Min Act: -0.1700
Data Index: 4489990 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.8435. Min Act: -0.1700
Data Index: 5842646 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.8123. Min Act: -0.1700
Data Index: 7605080 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7966. Min Act: -0.1700
Data Index: 3887027 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7966. Min Act: -0.1700
Data Index: 1088637 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7966. Min Act: -0.1700
Data Index: 2297362 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7810. Min Act: -0.1700
Data Index: 1147453 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7810. Min Act: -0.1700
Data Index: 1401180 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7810. Min Act: -0.1700
Data Index: 8733911 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7654. Min Act: -0.1700
Data Index: 8241584 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7654. Min Act: -0.1700
Data Index: 4707213 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7654. Min Act: -0.1700
Data Index: 6076896 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7810. Min Act: -0.1700
Data Index: 6221466 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7654. Min Act: -0.1700
Data Index: 6649486 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7497. Min Act: -0.1700
Data Index: 5769032 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7497. Min Act: -0.1700
Data Index: 2846875 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7654. Min Act: -0.1700
Data Index: 7018995 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7497. Min Act: -0.1700
Data Index: 347046 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9686. Min Range: -3.9686
Max Act: 3.7341. Min Act: -0.1700
Data Index: 2851332 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19