Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1527. Min Range: -7.1527
Max Act: 7.1527. Min Act: -0.1700
Data Index: 4119629 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1527. Min Range: -7.1527
Max Act: 7.0590. Min Act: -0.1700
Data Index: 3944523 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1527. Min Range: -7.1527
Max Act: 7.0590. Min Act: -0.1700
Data Index: 1937426 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1527. Min Range: -7.1527
Max Act: 7.0277. Min Act: -0.1700
Data Index: 8157208 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9652. Min Act: -0.1700
Data Index: 1973170 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9652. Min Act: -0.1700
Data Index: 8256324 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 7221931 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9340. Min Act: -0.1700
Data Index: 3382968 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 3674336 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 131816 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 228457 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 1498045 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 75205 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 6567686 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 6259427 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 5987666 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8402. Min Act: -0.1700
Data Index: 7118274 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.9027. Min Act: -0.1700
Data Index: 4823073 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 4616200 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1527. Min Range: -7.1527
Max Act: 6.8715. Min Act: -0.1700
Data Index: 7352240 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19