Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 854 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0736. Min Range: -8.0736
Max Act: 8.0736. Min Act: -0.1700
Data Index: 5073974 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0736. Min Range: -8.0736
Max Act: 8.0736. Min Act: -0.1700
Data Index: 8594176 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7923. Min Act: -0.1700
Data Index: 1706068 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7611. Min Act: -0.1700
Data Index: 2474031 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7923. Min Act: -0.1700
Data Index: 5483871 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7298. Min Act: -0.1700
Data Index: 1952909 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7298. Min Act: -0.1700
Data Index: 2874826 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.7298. Min Act: -0.1700
Data Index: 6060843 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6986. Min Act: -0.1700
Data Index: 7227666 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6986. Min Act: -0.1700
Data Index: 610440 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6673. Min Act: -0.1700
Data Index: 3638152 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6361. Min Act: -0.1700
Data Index: 4073392 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6361. Min Act: -0.1700
Data Index: 4963829 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6673. Min Act: -0.1700
Data Index: 97176 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6048. Min Act: -0.1700
Data Index: 8193818 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.5736. Min Act: -0.1700
Data Index: 1437580 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6048. Min Act: -0.1700
Data Index: 6372303 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6361. Min Act: -0.1700
Data Index: 1119091 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.6048. Min Act: -0.1700
Data Index: 4345373 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0736. Min Range: -8.0736
Max Act: 7.5736. Min Act: -0.1700
Data Index: 7480350 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19