Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 3632272 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.2361. Min Act: -0.1700
Data Index: 8049923 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.2048. Min Act: -0.1700
Data Index: 3912665 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.1736. Min Act: -0.1700
Data Index: 873173 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.1423. Min Act: -0.1700
Data Index: 3876929 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.1111. Min Act: -0.1700
Data Index: 65126 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0798. Min Act: -0.1700
Data Index: 7245628 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 2174906 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 4722490 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 434520 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 1193417 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 6683879 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 6238614 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 3121016 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4549. Min Range: -4.4549
Max Act: 4.0173. Min Act: -0.1700
Data Index: 993340 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4549. Min Range: -4.4549
Max Act: 3.9860. Min Act: -0.1700
Data Index: 7009824 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4549. Min Range: -4.4549
Max Act: 3.9548. Min Act: -0.1700
Data Index: 4432374 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4549. Min Range: -4.4549
Max Act: 3.9860. Min Act: -0.1700
Data Index: 3644541 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4549. Min Range: -4.4549
Max Act: 3.9860. Min Act: -0.1700
Data Index: 7360065 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4549. Min Range: -4.4549
Max Act: 3.9860. Min Act: -0.1700
Data Index: 1037834 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19