Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.2396. Min Act: -0.1700
Data Index: 6695651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.2084. Min Act: -0.1700
Data Index: 7225499 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.2084. Min Act: -0.1700
Data Index: 7210927 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.0833. Min Act: -0.1700
Data Index: 7654927 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.0833. Min Act: -0.1700
Data Index: 3174693 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.0521. Min Act: -0.1700
Data Index: 8809584 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2396. Min Range: -4.2396
Max Act: 4.0208. Min Act: -0.1700
Data Index: 5658577 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.9896. Min Act: -0.1700
Data Index: 4944990 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.9896. Min Act: -0.1700
Data Index: 7427554 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.9583. Min Act: -0.1700
Data Index: 5922504 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.9896. Min Act: -0.1700
Data Index: 899777 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 5635647 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 4698365 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 1346948 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 3080949 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 8109147 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8958. Min Act: -0.1700
Data Index: 899772 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8645. Min Act: -0.1700
Data Index: 230429 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8645. Min Act: -0.1700
Data Index: 6336271 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2396. Min Range: -4.2396
Max Act: 3.8332. Min Act: -0.1700
Data Index: 3132320 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19