Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0504. Min Range: -6.0504
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7155319 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.8317. Min Act: -0.1700
Data Index: 251722 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.7692. Min Act: -0.1700
Data Index: 112226 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.7379. Min Act: -0.1700
Data Index: 77726 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.7379. Min Act: -0.1700
Data Index: 648356 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.7379. Min Act: -0.1700
Data Index: 1238391 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.6442. Min Act: -0.1700
Data Index: 3858385 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.6442. Min Act: -0.1700
Data Index: 3217616 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.6754. Min Act: -0.1700
Data Index: 6619508 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6619504 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.5504. Min Act: -0.1700
Data Index: 251737 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.6129. Min Act: -0.1700
Data Index: 4446135 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.5192. Min Act: -0.1700
Data Index: 5793381 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.4879. Min Act: -0.1700
Data Index: 2266022 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.4879. Min Act: -0.1700
Data Index: 7319500 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3984473 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.4567. Min Act: -0.1700
Data Index: 5397156 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.4567. Min Act: -0.1700
Data Index: 648354 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.4254. Min Act: -0.1700
Data Index: 8100164 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0504. Min Range: -6.0504
Max Act: 5.3942. Min Act: -0.1700
Data Index: 4020113 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19