Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.4705. Min Act: -0.1700
Data Index: 4621917 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.3455. Min Act: -0.1700
Data Index: 1695124 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.2518. Min Act: -0.1700
Data Index: 8187975 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.2518. Min Act: -0.1700
Data Index: 7339266 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.2518. Min Act: -0.1700
Data Index: 5459748 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.2205. Min Act: -0.1700
Data Index: 4316603 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.2205. Min Act: -0.1700
Data Index: 7092219 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1892. Min Act: -0.1700
Data Index: 5705543 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1892. Min Act: -0.1700
Data Index: 3438768 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1892. Min Act: -0.1700
Data Index: 7716260 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1580. Min Act: -0.1700
Data Index: 7502035 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1580. Min Act: -0.1700
Data Index: 5132234 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1580. Min Act: -0.1700
Data Index: 1873262 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1267. Min Act: -0.1700
Data Index: 6992135 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1580. Min Act: -0.1700
Data Index: 6785756 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1267. Min Act: -0.1700
Data Index: 919045 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1267. Min Act: -0.1700
Data Index: 239074 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.0955. Min Act: -0.1700
Data Index: 7977088 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.0955. Min Act: -0.1700
Data Index: 4838854 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4705. Min Range: -4.4705
Max Act: 4.1267. Min Act: -0.1700
Data Index: 2789015 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19