Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9851. Min Act: -0.1700
Data Index: 4114095 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9693. Min Act: -0.1700
Data Index: 1744513 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9535. Min Act: -0.1700
Data Index: 5777873 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9535. Min Act: -0.1700
Data Index: 8448366 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9376. Min Act: -0.1700
Data Index: 3301518 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9218. Min Act: -0.1700
Data Index: 186035 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9218. Min Act: -0.1700
Data Index: 5626830 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9059. Min Act: -0.1700
Data Index: 6450721 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.9059. Min Act: -0.1700
Data Index: 4093535 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8901. Min Act: -0.1700
Data Index: 364404 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8901. Min Act: -0.1700
Data Index: 682960 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8901. Min Act: -0.1700
Data Index: 4703138 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8901. Min Act: -0.1700
Data Index: 2020322 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8742. Min Act: -0.1700
Data Index: 8250030 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8742. Min Act: -0.1700
Data Index: 3528008 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8901. Min Act: -0.1700
Data Index: 6790158 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8742. Min Act: -0.1700
Data Index: 1259494 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8583. Min Act: -0.1700
Data Index: 3506279 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8583. Min Act: -0.1700
Data Index: 693373 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9851. Min Range: -2.9851
Max Act: 2.8583. Min Act: -0.1700
Data Index: 5982110 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19