Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0940. Min Range: -7.0940
Max Act: 7.0940. Min Act: -0.1700
Data Index: 701629 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.7815. Min Act: -0.1700
Data Index: 1817531 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.7190. Min Act: -0.1700
Data Index: 2882904 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.5940. Min Act: -0.1700
Data Index: 5863817 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.6253. Min Act: -0.1700
Data Index: 8647403 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.5315. Min Act: -0.1700
Data Index: 5857990 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.4690. Min Act: -0.1700
Data Index: 3128022 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.5003. Min Act: -0.1700
Data Index: 4406797 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1844871 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.3440. Min Act: -0.1700
Data Index: 13059 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.3753. Min Act: -0.1700
Data Index: 6347218 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.3753. Min Act: -0.1700
Data Index: 1610110 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.3128. Min Act: -0.1700
Data Index: 3032636 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2815. Min Act: -0.1700
Data Index: 4046659 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2815. Min Act: -0.1700
Data Index: 6641328 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2815. Min Act: -0.1700
Data Index: 1610108 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2815. Min Act: -0.1700
Data Index: 627907 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2815. Min Act: -0.1700
Data Index: 7184660 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2503. Min Act: -0.1700
Data Index: 8175763 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0940. Min Range: -7.0940
Max Act: 6.2503. Min Act: -0.1700
Data Index: 3606165 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19