Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.3053. Min Act: -0.1700
Data Index: 4096766 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3053. Min Range: -5.3053
Max Act: 5.0866. Min Act: -0.1700
Data Index: 8228419 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9928. Min Act: -0.1700
Data Index: 3637188 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9616. Min Act: -0.1700
Data Index: 2666026 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9616. Min Act: -0.1700
Data Index: 158772 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.9303. Min Act: -0.1700
Data Index: 3137380 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8678. Min Act: -0.1700
Data Index: 4445837 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8991. Min Act: -0.1700
Data Index: 7449498 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8678. Min Act: -0.1700
Data Index: 7726064 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8366. Min Act: -0.1700
Data Index: 1472885 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8053. Min Act: -0.1700
Data Index: 997885 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.8053. Min Act: -0.1700
Data Index: 6977540 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7428. Min Act: -0.1700
Data Index: 4218787 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7428. Min Act: -0.1700
Data Index: 3107678 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7116. Min Act: -0.1700
Data Index: 3320697 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7116. Min Act: -0.1700
Data Index: 7263261 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7428. Min Act: -0.1700
Data Index: 7004939 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.7116. Min Act: -0.1700
Data Index: 8210274 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.6803. Min Act: -0.1700
Data Index: 1691741 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3053. Min Range: -5.3053
Max Act: 4.6803. Min Act: -0.1700
Data Index: 86392 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19