Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.2871. Min Act: -0.1700
Data Index: 6558732 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.2210. Min Act: -0.1700
Data Index: 1805466 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1712. Min Act: -0.1700
Data Index: 5279949 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1712. Min Act: -0.1700
Data Index: 6546490 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1545. Min Act: -0.1700
Data Index: 5998735 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1712. Min Act: -0.1700
Data Index: 1929648 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1545. Min Act: -0.1700
Data Index: 4049352 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1712. Min Act: -0.1700
Data Index: 8793582 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1379. Min Act: -0.1700
Data Index: 857038 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 6866196 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1379. Min Act: -0.1700
Data Index: 7156230 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 5757839 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 5006467 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 5949423 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 5541170 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 6384948 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 7542470 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1044. Min Act: -0.1700
Data Index: 3683574 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.1212. Min Act: -0.1700
Data Index: 6815794 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2871. Min Range: -2.2871
Max Act: 2.0877. Min Act: -0.1700
Data Index: 1403160 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19