Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0745. Min Range: -4.0745
Max Act: 4.0745. Min Act: -0.1700
Data Index: 1112371 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.9808. Min Act: -0.1700
Data Index: 7400927 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0745. Min Range: -4.0745
Max Act: 4.0120. Min Act: -0.1700
Data Index: 8773622 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0745. Min Range: -4.0745
Max Act: 4.0120. Min Act: -0.1700
Data Index: 1052632 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.9808. Min Act: -0.1700
Data Index: 6689098 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8870. Min Act: -0.1700
Data Index: 7441975 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8870. Min Act: -0.1700
Data Index: 2007096 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8870. Min Act: -0.1700
Data Index: 2537585 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8557. Min Act: -0.1700
Data Index: 949246 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8557. Min Act: -0.1700
Data Index: 4730706 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8557. Min Act: -0.1700
Data Index: 8371289 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8244. Min Act: -0.1700
Data Index: 7894717 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.8244. Min Act: -0.1700
Data Index: 1657062 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7932. Min Act: -0.1700
Data Index: 1152972 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7932. Min Act: -0.1700
Data Index: 6113900 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7932. Min Act: -0.1700
Data Index: 914831 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7932. Min Act: -0.1700
Data Index: 1360831 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7932. Min Act: -0.1700
Data Index: 4123578 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7619. Min Act: -0.1700
Data Index: 5914782 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0745. Min Range: -4.0745
Max Act: 3.7619. Min Act: -0.1700
Data Index: 373730 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19