Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7299249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 4542733 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 3845462 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2912745 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 793248 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 2146259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 8195388 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 6683962 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2369239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2644838 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.1738. Min Act: -0.1700
Data Index: 2719323 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2897931 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 284960 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.1738. Min Act: -0.1700
Data Index: 2948019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 3690201 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.1738. Min Act: -0.1700
Data Index: 3937431 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 4442315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 4542734 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 5088437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.1738. Min Act: -0.1700
Data Index: 5101564 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19