Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 742 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5759. Min Range: -5.5759
Max Act: 5.5759. Min Act: -0.1700
Data Index: 4041574 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5759. Min Range: -5.5759
Max Act: 5.3572. Min Act: -0.1700
Data Index: 3490064 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5759. Min Range: -5.5759
Max Act: 5.2322. Min Act: -0.1700
Data Index: 8685384 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5759. Min Range: -5.5759
Max Act: 5.1072. Min Act: -0.1700
Data Index: 5065486 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5759. Min Range: -5.5759
Max Act: 5.2009. Min Act: -0.1700
Data Index: 7244656 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.9822. Min Act: -0.1700
Data Index: 2041922 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.8884. Min Act: -0.1700
Data Index: 2050363 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.7009. Min Act: -0.1700
Data Index: 878662 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.6697. Min Act: -0.1700
Data Index: 8480008 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.6384. Min Act: -0.1700
Data Index: 7410973 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.6384. Min Act: -0.1700
Data Index: 4364839 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5759. Min Act: -0.1700
Data Index: 7359300 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1339044 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.4822. Min Act: -0.1700
Data Index: 4606709 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5447. Min Act: -0.1700
Data Index: 2019241 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5759. Min Act: -0.1700
Data Index: 4043753 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5134. Min Act: -0.1700
Data Index: 1667130 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5447. Min Act: -0.1700
Data Index: 2403511 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5134. Min Act: -0.1700
Data Index: 4501759 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5759. Min Range: -5.5759
Max Act: 4.5134. Min Act: -0.1700
Data Index: 6034744 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19