Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.4785. Min Act: -0.1700
Data Index: 6002592 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3848. Min Act: -0.1700
Data Index: 6631026 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3848. Min Act: -0.1700
Data Index: 6543011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3848. Min Act: -0.1700
Data Index: 2304264 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3535. Min Act: -0.1700
Data Index: 4728587 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3848. Min Act: -0.1700
Data Index: 3963705 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3535. Min Act: -0.1700
Data Index: 6504137 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3535. Min Act: -0.1700
Data Index: 8784632 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3535. Min Act: -0.1700
Data Index: 1144100 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3535. Min Act: -0.1700
Data Index: 8055283 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8371034 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8432497 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8450402 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 6390645 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 5701638 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8030456 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 3962147 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 2239861 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 5177786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4785. Min Range: -4.4785
Max Act: 4.3223. Min Act: -0.1700
Data Index: 6600328 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19