Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.9579. Min Act: -0.1700
Data Index: 1954902 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.7833. Min Act: -0.1700
Data Index: 7180433 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.7673. Min Act: -0.1700
Data Index: 630412 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.7514. Min Act: -0.1700
Data Index: 3185900 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.7354. Min Act: -0.1700
Data Index: 3206265 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.7034. Min Act: -0.1700
Data Index: 3419094 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6874. Min Act: -0.1700
Data Index: 7984454 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6393. Min Act: -0.1700
Data Index: 2809564 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6554. Min Act: -0.1700
Data Index: 2576956 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6233. Min Act: -0.1700
Data Index: 2693572 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6233. Min Act: -0.1700
Data Index: 8592724 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6072. Min Act: -0.1700
Data Index: 4987895 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6072. Min Act: -0.1700
Data Index: 1064280 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6072. Min Act: -0.1700
Data Index: 839105 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6072. Min Act: -0.1700
Data Index: 1102649 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6233. Min Act: -0.1700
Data Index: 5766670 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.5911. Min Act: -0.1700
Data Index: 647443 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.6072. Min Act: -0.1700
Data Index: 382515 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.5911. Min Act: -0.1700
Data Index: 1194952 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9579. Min Range: -2.9579
Max Act: 2.5911. Min Act: -0.1700
Data Index: 7663158 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19