Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.4890. Min Act: -0.1700
Data Index: 503230 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.5515. Min Act: -0.1700
Data Index: 7655443 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.4890. Min Act: -0.1700
Data Index: 3747854 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.4265. Min Act: -0.1700
Data Index: 6426140 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.3015. Min Act: -0.1700
Data Index: 357909 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.1765. Min Act: -0.1700
Data Index: 1040985 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.1140. Min Act: -0.1700
Data Index: 8405010 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.0515. Min Act: -0.1700
Data Index: 8122068 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.0515. Min Act: -0.1700
Data Index: 6252784 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5515. Min Range: -8.5515
Max Act: 8.1140. Min Act: -0.1700
Data Index: 4316065 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 8656354 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 4996334 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 7904496 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 3551548 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 7908725 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9890. Min Act: -0.1700
Data Index: 3579920 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.9265. Min Act: -0.1700
Data Index: 8345993 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.8640. Min Act: -0.1700
Data Index: 2300572 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.8640. Min Act: -0.1700
Data Index: 7950389 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5515. Min Range: -8.5515
Max Act: 7.8640. Min Act: -0.1700
Data Index: 725174 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19