Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.2799. Min Act: -0.1700
Data Index: 8146845 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.2799. Min Act: -0.1700
Data Index: 572303 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.2174. Min Act: -0.1700
Data Index: 6160741 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.2174. Min Act: -0.1700
Data Index: 3722894 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1861. Min Act: -0.1700
Data Index: 5116133 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 7312846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1861. Min Act: -0.1700
Data Index: 2790735 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1861. Min Act: -0.1700
Data Index: 644521 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 5569910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 1577510 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1549. Min Act: -0.1700
Data Index: 3362235 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1236. Min Act: -0.1700
Data Index: 5259397 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.1236. Min Act: -0.1700
Data Index: 3528101 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 6269742 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 482856 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 5259378 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0611. Min Act: -0.1700
Data Index: 5259388 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 3528102 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 4756281 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2799. Min Range: -6.2799
Max Act: 6.0924. Min Act: -0.1700
Data Index: 5569912 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19