Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2231 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2435. Min Range: -6.2435
Max Act: 6.2435. Min Act: -0.1700
Data Index: 3375000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1700567 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 2201431 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 71201 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6181978 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6281063 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 8722239 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 8140080 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1856934 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 5885177 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9310. Min Act: -0.1700
Data Index: 908305 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9623. Min Act: -0.1700
Data Index: 4849555 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9310. Min Act: -0.1700
Data Index: 944283 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.8998. Min Act: -0.1700
Data Index: 2649022 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9310. Min Act: -0.1700
Data Index: 3635833 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.8998. Min Act: -0.1700
Data Index: 910003 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.8998. Min Act: -0.1700
Data Index: 4534052 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.8998. Min Act: -0.1700
Data Index: 4671025 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.9310. Min Act: -0.1700
Data Index: 8448406 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2435. Min Range: -6.2435
Max Act: 5.8998. Min Act: -0.1700
Data Index: 2195386 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19