Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 688 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.2055. Min Act: -0.1700
Data Index: 5440857 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 3482447 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 7580976 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.1117. Min Act: -0.1700
Data Index: 6092759 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.1117. Min Act: -0.1700
Data Index: 6597040 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0805. Min Act: -0.1700
Data Index: 5609896 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0492. Min Act: -0.1700
Data Index: 1136766 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0492. Min Act: -0.1700
Data Index: 8333209 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0180. Min Act: -0.1700
Data Index: 2159994 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9867. Min Act: -0.1700
Data Index: 4017954 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9867. Min Act: -0.1700
Data Index: 3768106 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9867. Min Act: -0.1700
Data Index: 7882282 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0180. Min Act: -0.1700
Data Index: 1955680 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2055. Min Range: -5.2055
Max Act: 5.0180. Min Act: -0.1700
Data Index: 1955692 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9555. Min Act: -0.1700
Data Index: 2219644 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9867. Min Act: -0.1700
Data Index: 6392689 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9242. Min Act: -0.1700
Data Index: 20526 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9555. Min Act: -0.1700
Data Index: 1251683 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9555. Min Act: -0.1700
Data Index: 6066365 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2055. Min Range: -5.2055
Max Act: 4.9555. Min Act: -0.1700
Data Index: 4259782 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19