Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.4570. Min Act: -0.1700
Data Index: 5314584 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3473. Min Act: -0.1700
Data Index: 756005 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3473. Min Act: -0.1700
Data Index: 1032314 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3159. Min Act: -0.1700
Data Index: 2274932 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3159. Min Act: -0.1700
Data Index: 7551078 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2845. Min Act: -0.1700
Data Index: 6536313 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3473. Min Act: -0.1700
Data Index: 3484460 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3316. Min Act: -0.1700
Data Index: 6883022 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3159. Min Act: -0.1700
Data Index: 7821322 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3002. Min Act: -0.1700
Data Index: 6166030 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3002. Min Act: -0.1700
Data Index: 7235355 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2845. Min Act: -0.1700
Data Index: 6788520 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2688. Min Act: -0.1700
Data Index: 773130 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.3002. Min Act: -0.1700
Data Index: 1531139 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2845. Min Act: -0.1700
Data Index: 7623573 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2845. Min Act: -0.1700
Data Index: 8562487 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2688. Min Act: -0.1700
Data Index: 608999 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2531. Min Act: -0.1700
Data Index: 7743724 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2688. Min Act: -0.1700
Data Index: 7455972 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4570. Min Range: -3.4570
Max Act: 3.2845. Min Act: -0.1700
Data Index: 4055887 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19