Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.6048. Min Act: -0.1700
Data Index: 978914 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.4638. Min Act: -0.1700
Data Index: 6144517 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.4638. Min Act: -0.1700
Data Index: 3096196 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.3698. Min Act: -0.1700
Data Index: 2015758 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.3855. Min Act: -0.1700
Data Index: 6831252 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.3541. Min Act: -0.1700
Data Index: 4003806 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.3698. Min Act: -0.1700
Data Index: 6549777 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.3070. Min Act: -0.1700
Data Index: 4059245 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2913. Min Act: -0.1700
Data Index: 3810498 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2599. Min Act: -0.1700
Data Index: 8827325 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2756. Min Act: -0.1700
Data Index: 8204816 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2442. Min Act: -0.1700
Data Index: 5122183 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2599. Min Act: -0.1700
Data Index: 3737502 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2599. Min Act: -0.1700
Data Index: 4394880 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2756. Min Act: -0.1700
Data Index: 5346272 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2599. Min Act: -0.1700
Data Index: 4342405 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2442. Min Act: -0.1700
Data Index: 2960347 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2599. Min Act: -0.1700
Data Index: 1217110 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2285. Min Act: -0.1700
Data Index: 2015757 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6048. Min Range: -3.6048
Max Act: 3.2285. Min Act: -0.1700
Data Index: 5607913 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19