Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1392. Min Range: -8.1392
Max Act: 8.1392. Min Act: -0.1700
Data Index: 1972523 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.8892. Min Act: -0.1700
Data Index: 4738387 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.7330. Min Act: -0.1700
Data Index: 6685051 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.6705. Min Act: -0.1700
Data Index: 6685049 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.5142. Min Act: -0.1700
Data Index: 5446842 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.4830. Min Act: -0.1700
Data Index: 6685061 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.4517. Min Act: -0.1700
Data Index: 5186878 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.4517. Min Act: -0.1700
Data Index: 7868491 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.3892. Min Act: -0.1700
Data Index: 1894829 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.3892. Min Act: -0.1700
Data Index: 5644734 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.3580. Min Act: -0.1700
Data Index: 6329152 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.3580. Min Act: -0.1700
Data Index: 4738389 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.3267. Min Act: -0.1700
Data Index: 2276904 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.2955. Min Act: -0.1700
Data Index: 3701591 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.2642. Min Act: -0.1700
Data Index: 4144131 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.2330. Min Act: -0.1700
Data Index: 4076469 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.2017. Min Act: -0.1700
Data Index: 4575079 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.1705. Min Act: -0.1700
Data Index: 6688095 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.1705. Min Act: -0.1700
Data Index: 2551007 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1392. Min Range: -8.1392
Max Act: 7.1705. Min Act: -0.1700
Data Index: 5237373 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19