Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1613. Min Range: -8.1613
Max Act: 8.1613. Min Act: -0.1700
Data Index: 7854602 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.7238. Min Act: -0.1700
Data Index: 8371085 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.6925. Min Act: -0.1700
Data Index: 3732086 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.5050. Min Act: -0.1700
Data Index: 1716756 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.4425. Min Act: -0.1700
Data Index: 4802847 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.4113. Min Act: -0.1700
Data Index: 3541266 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.4113. Min Act: -0.1700
Data Index: 4706170 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.4113. Min Act: -0.1700
Data Index: 7976976 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.3800. Min Act: -0.1700
Data Index: 2504821 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.3800. Min Act: -0.1700
Data Index: 3619728 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.3800. Min Act: -0.1700
Data Index: 2018615 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2863. Min Act: -0.1700
Data Index: 5100895 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2863. Min Act: -0.1700
Data Index: 2762472 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2863. Min Act: -0.1700
Data Index: 8099348 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2550. Min Act: -0.1700
Data Index: 3494194 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2550. Min Act: -0.1700
Data Index: 1419625 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2550. Min Act: -0.1700
Data Index: 545939 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2238. Min Act: -0.1700
Data Index: 707995 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.2238. Min Act: -0.1700
Data Index: 6850978 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1613. Min Range: -8.1613
Max Act: 7.1925. Min Act: -0.1700
Data Index: 3294845 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19