Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3447. Min Range: -8.3447
Max Act: 8.3447. Min Act: -0.1700
Data Index: 5586721 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3447. Min Range: -8.3447
Max Act: 8.2197. Min Act: -0.1700
Data Index: 5823022 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3447. Min Range: -8.3447
Max Act: 8.0322. Min Act: -0.1700
Data Index: 2584638 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.7822. Min Act: -0.1700
Data Index: 2874803 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.7822. Min Act: -0.1700
Data Index: 1561242 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.7197. Min Act: -0.1700
Data Index: 8796927 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.6572. Min Act: -0.1700
Data Index: 6722223 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.6572. Min Act: -0.1700
Data Index: 4772147 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.6572. Min Act: -0.1698
Data Index: 4592841 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.5947. Min Act: -0.1700
Data Index: 4265920 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.5947. Min Act: -0.1700
Data Index: 1577564 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.5947. Min Act: -0.1700
Data Index: 4185044 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.5322. Min Act: -0.1700
Data Index: 3872974 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4697. Min Act: -0.1700
Data Index: 344751 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4697. Min Act: -0.1700
Data Index: 3839910 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4697. Min Act: -0.1700
Data Index: 5581322 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4697. Min Act: -0.1700
Data Index: 509892 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4697. Min Act: -0.1700
Data Index: 2712649 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4072. Min Act: -0.1700
Data Index: 2265185 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3447. Min Range: -8.3447
Max Act: 7.4072. Min Act: -0.1700
Data Index: 2784503 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19