Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.6370. Min Act: -0.1700
Data Index: 7804281 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5745. Min Act: -0.1700
Data Index: 6160950 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5433. Min Act: -0.1700
Data Index: 1497318 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5433. Min Act: -0.1700
Data Index: 5803465 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5433. Min Act: -0.1700
Data Index: 715452 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 7415812 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 21581 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 2144632 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 1971664 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 7449895 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4495. Min Act: -0.1700
Data Index: 7528033 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4808. Min Act: -0.1700
Data Index: 1230790 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4495. Min Act: -0.1700
Data Index: 1251431 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.5120. Min Act: -0.1700
Data Index: 4191126 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4808. Min Act: -0.1700
Data Index: 1486167 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4495. Min Act: -0.1700
Data Index: 2551115 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4183. Min Act: -0.1700
Data Index: 268309 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4495. Min Act: -0.1700
Data Index: 111998 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4495. Min Act: -0.1700
Data Index: 6717929 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6370. Min Range: -4.6370
Max Act: 4.4808. Min Act: -0.1700
Data Index: 3548309 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19