Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1115. Min Range: -5.1115
Max Act: 5.1115. Min Act: -0.1700
Data Index: 12621 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1115. Min Range: -5.1115
Max Act: 5.0802. Min Act: -0.1700
Data Index: 8778754 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1115. Min Range: -5.1115
Max Act: 5.0490. Min Act: -0.1700
Data Index: 8560961 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.9865. Min Act: -0.1700
Data Index: 3904431 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.9552. Min Act: -0.1700
Data Index: 8554350 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.9240. Min Act: -0.1700
Data Index: 8349100 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.9240. Min Act: -0.1700
Data Index: 1619565 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.8615. Min Act: -0.1700
Data Index: 128833 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.8302. Min Act: -0.1700
Data Index: 474632 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.8302. Min Act: -0.1700
Data Index: 6672336 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7990. Min Act: -0.1700
Data Index: 8554353 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7990. Min Act: -0.1700
Data Index: 7718645 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7677. Min Act: -0.1700
Data Index: 5495380 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7677. Min Act: -0.1700
Data Index: 1563996 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7052. Min Act: -0.1700
Data Index: 8229436 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6427. Min Act: -0.1700
Data Index: 6837223 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6740. Min Act: -0.1700
Data Index: 1017316 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6740. Min Act: -0.1700
Data Index: 870369 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6740. Min Act: -0.1700
Data Index: 3878305 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6115. Min Act: -0.1700
Data Index: 3138035 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19