Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.2295. Min Act: -0.1700
Data Index: 2133204 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.1983. Min Act: -0.1700
Data Index: 4566400 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.0732. Min Act: -0.1700
Data Index: 7824958 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.0732. Min Act: -0.1700
Data Index: 7885406 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.0107. Min Act: -0.1700
Data Index: 7494900 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2295. Min Range: -4.2295
Max Act: 4.0107. Min Act: -0.1700
Data Index: 6397879 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9638. Min Act: -0.1700
Data Index: 7561310 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9795. Min Act: -0.1700
Data Index: 4991286 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9638. Min Act: -0.1700
Data Index: 1911914 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9326. Min Act: -0.1700
Data Index: 5465835 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9326. Min Act: -0.1700
Data Index: 2999257 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9169. Min Act: -0.1700
Data Index: 4030994 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9482. Min Act: -0.1700
Data Index: 1917637 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9169. Min Act: -0.1700
Data Index: 5279364 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.8857. Min Act: -0.1700
Data Index: 1465187 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.9013. Min Act: -0.1700
Data Index: 8718765 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.8700. Min Act: -0.1700
Data Index: 6558504 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.8700. Min Act: -0.1700
Data Index: 7870493 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.8857. Min Act: -0.1700
Data Index: 4991285 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2295. Min Range: -4.2295
Max Act: 3.8700. Min Act: -0.1700
Data Index: 2942731 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19