Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5727. Min Act: -0.1700
Data Index: 6216177 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 7724464 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 6749058 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 7543090 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 192989 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 5881813 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 3548245 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 5403941 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 1065303 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 652650 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4164. Min Act: -0.1700
Data Index: 4437518 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4477. Min Act: -0.1700
Data Index: 5407699 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4477. Min Act: -0.1700
Data Index: 6495852 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3326190 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 7999557 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 2316880 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5737044 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4789. Min Act: -0.1700
Data Index: 4783306 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4477. Min Act: -0.1700
Data Index: 6366263 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.4164. Min Act: -0.1700
Data Index: 854110 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19