Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.5572. Min Act: -0.1700
Data Index: 8095492 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.5572. Min Act: -0.1699
Data Index: 650848 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4958. Min Act: -0.1700
Data Index: 1996004 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4783. Min Act: -0.1698
Data Index: 6137820 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4783. Min Act: -0.1700
Data Index: 1424069 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4783. Min Act: -0.1698
Data Index: 8517987 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4607. Min Act: -0.1700
Data Index: 7012945 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4519. Min Act: -0.1700
Data Index: 8102458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4607. Min Act: -0.1700
Data Index: 7084892 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4431. Min Act: -0.1700
Data Index: 2360049 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4431. Min Act: -0.1700
Data Index: 1095546 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4431. Min Act: -0.1700
Data Index: 4075468 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4343. Min Act: -0.1700
Data Index: 7761165 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4431. Min Act: -0.1699
Data Index: 6259090 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4255. Min Act: -0.1623
Data Index: 8292679 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4167. Min Act: -0.1700
Data Index: 1803926 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4167. Min Act: -0.1700
Data Index: 5158877 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4255. Min Act: -0.1700
Data Index: 303282 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4255. Min Act: -0.1700
Data Index: 2765949 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5572. Min Range: -1.5572
Max Act: 1.4167. Min Act: -0.1700
Data Index: 1624803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19