Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.9045. Min Act: -0.1700
Data Index: 576677 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.8420. Min Act: -0.1700
Data Index: 4963904 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.8107. Min Act: -0.1700
Data Index: 2916842 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.7795. Min Act: -0.1700
Data Index: 7138038 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.7482. Min Act: -0.1700
Data Index: 1288825 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.7170. Min Act: -0.1700
Data Index: 7314979 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.7170. Min Act: -0.1700
Data Index: 2770625 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.5607. Min Act: -0.1700
Data Index: 7655376 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.5607. Min Act: -0.1700
Data Index: 7395251 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.5607. Min Act: -0.1700
Data Index: 8445807 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.5295. Min Act: -0.1700
Data Index: 536462 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.5607. Min Act: -0.1700
Data Index: 3918164 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4982. Min Act: -0.1700
Data Index: 1288826 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4670. Min Act: -0.1700
Data Index: 6604216 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4982. Min Act: -0.1700
Data Index: 5362539 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5268822 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4357. Min Act: -0.1700
Data Index: 8632680 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4357. Min Act: -0.1700
Data Index: 8817658 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.4045. Min Act: -0.1700
Data Index: 257284 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9045. Min Range: -4.9045
Max Act: 4.3732. Min Act: -0.1700
Data Index: 8641496 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19