Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1635. Min Range: -10.1635
Max Act: 10.1635. Min Act: -0.1700
Data Index: 4755194 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1635. Min Range: -10.1635
Max Act: 9.6010. Min Act: -0.1700
Data Index: 876617 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1635. Min Range: -10.1635
Max Act: 9.1010. Min Act: -0.1683
Data Index: 7174420 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.9135. Min Act: -0.1700
Data Index: 7313185 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.9135. Min Act: -0.1700
Data Index: 4648961 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.8510. Min Act: -0.1700
Data Index: 4821068 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.6635. Min Act: -0.1700
Data Index: 7643407 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.6322. Min Act: -0.1700
Data Index: 5875946 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.4135. Min Act: -0.1700
Data Index: 7057605 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.3510. Min Act: -0.1698
Data Index: 829537 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.3510. Min Act: -0.1700
Data Index: 4827325 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.3510. Min Act: -0.1700
Data Index: 1237994 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.3197. Min Act: -0.1700
Data Index: 4002353 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.2260. Min Act: -0.1700
Data Index: 8749083 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.1947. Min Act: -0.1700
Data Index: 7101166 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.2260. Min Act: -0.1700
Data Index: 2193963 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.2260. Min Act: -0.1699
Data Index: 320009 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.1947. Min Act: -0.1700
Data Index: 6152865 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.1947. Min Act: -0.1699
Data Index: 3153255 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1635. Min Range: -10.1635
Max Act: 8.1635. Min Act: -0.1700
Data Index: 5754456 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19