Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6161 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.5929. Min Act: -0.1700
Data Index: 5836328 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.5304. Min Act: -0.1700
Data Index: 3636036 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4991. Min Act: -0.1700
Data Index: 1799728 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4991. Min Act: -0.1700
Data Index: 3330662 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4679. Min Act: -0.1700
Data Index: 5926821 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4679. Min Act: -0.1700
Data Index: 5696565 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4679. Min Act: -0.1700
Data Index: 282969 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4376273 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.4054. Min Act: -0.1699
Data Index: 3655868 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.3741. Min Act: -0.1700
Data Index: 7770668 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.3429. Min Act: -0.1700
Data Index: 1887826 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.3116. Min Act: -0.1700
Data Index: 2906897 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.3116. Min Act: -0.1700
Data Index: 5443698 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2804. Min Act: -0.1700
Data Index: 5443699 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2804. Min Act: -0.1700
Data Index: 6349810 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2804. Min Act: -0.1700
Data Index: 8445022 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2804. Min Act: -0.1700
Data Index: 2736974 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2491. Min Act: -0.1700
Data Index: 3601690 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.2179. Min Act: -0.1700
Data Index: 2823998 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5929. Min Range: -5.5929
Max Act: 5.1866. Min Act: -0.1700
Data Index: 1383648 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19