Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 392 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0362. Min Range: -6.0362
Max Act: 6.0362. Min Act: -0.1700
Data Index: 1965775 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0362. Min Range: -6.0362
Max Act: 6.0362. Min Act: -0.1700
Data Index: 6246707 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.9737. Min Act: -0.1700
Data Index: 3885693 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.9424. Min Act: -0.1700
Data Index: 4286924 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8487. Min Act: -0.1700
Data Index: 2568553 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8799. Min Act: -0.1700
Data Index: 984163 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8174. Min Act: -0.1700
Data Index: 8363555 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8174. Min Act: -0.1700
Data Index: 5784166 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8174. Min Act: -0.1700
Data Index: 5889245 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8174. Min Act: -0.1700
Data Index: 234839 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7862. Min Act: -0.1700
Data Index: 1746501 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.8174. Min Act: -0.1700
Data Index: 6696501 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7862. Min Act: -0.1700
Data Index: 655619 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7549. Min Act: -0.1700
Data Index: 870767 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7549. Min Act: -0.1700
Data Index: 5582356 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7862. Min Act: -0.1700
Data Index: 2815325 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.6924. Min Act: -0.1700
Data Index: 6830245 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7237. Min Act: -0.1700
Data Index: 474217 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.6924. Min Act: -0.1700
Data Index: 3741069 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0362. Min Range: -6.0362
Max Act: 5.7237. Min Act: -0.1700
Data Index: 1970276 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19