Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.7743. Min Act: -0.1698
Data Index: 1237969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.7743. Min Act: -0.1697
Data Index: 4920390 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3164023 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.7118. Min Act: -0.1700
Data Index: 8231932 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1387986 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1099134 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.5243. Min Act: -0.1700
Data Index: 7542624 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.4931. Min Act: -0.1700
Data Index: 4158928 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3681. Min Act: -0.1699
Data Index: 3369120 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3681. Min Act: -0.1700
Data Index: 8455574 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3368. Min Act: -0.1698
Data Index: 7617222 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3368. Min Act: -0.1700
Data Index: 5845445 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.2743. Min Act: -0.1700
Data Index: 7880497 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3056. Min Act: -0.1700
Data Index: 56907 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3056. Min Act: -0.1693
Data Index: 6370464 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.3056. Min Act: -0.1700
Data Index: 4744434 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.2743. Min Act: -0.1700
Data Index: 2421795 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.2431. Min Act: -0.1700
Data Index: 2935191 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.2743. Min Act: -0.1700
Data Index: 2531234 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7743. Min Range: -5.7743
Max Act: 5.2743. Min Act: -0.1700
Data Index: 356116 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19