Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2802. Min Range: -6.2802
Max Act: 6.2802. Min Act: -0.1700
Data Index: 1000648 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.9677. Min Act: -0.1700
Data Index: 8119565 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.7802. Min Act: -0.1700
Data Index: 299907 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.7177. Min Act: -0.1700
Data Index: 7110457 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1027568 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.7177. Min Act: -0.1700
Data Index: 1676807 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6865. Min Act: -0.1700
Data Index: 2502605 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6865. Min Act: -0.1700
Data Index: 6750947 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6552. Min Act: -0.1700
Data Index: 37254 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6240. Min Act: -0.1700
Data Index: 7781606 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6240. Min Act: -0.1700
Data Index: 8108157 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6240. Min Act: -0.1700
Data Index: 432221 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6240. Min Act: -0.1700
Data Index: 5076368 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.6240. Min Act: -0.1700
Data Index: 2138408 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 5447624 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7328109 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7054559 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5615. Min Act: -0.1700
Data Index: 5121077 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5615. Min Act: -0.1700
Data Index: 7544785 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2802. Min Range: -6.2802
Max Act: 5.5615. Min Act: -0.1700
Data Index: 6768069 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19