Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.4760. Min Act: -0.1700
Data Index: 795927 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.4135. Min Act: -0.1700
Data Index: 7997177 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.3823. Min Act: -0.1700
Data Index: 8635848 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.3510. Min Act: -0.1700
Data Index: 670723 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.2885. Min Act: -0.1700
Data Index: 3996510 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.2573. Min Act: -0.1700
Data Index: 3712215 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.2573. Min Act: -0.1700
Data Index: 1761279 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.2573. Min Act: -0.1700
Data Index: 8506115 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1948. Min Act: -0.1700
Data Index: 2736212 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.2260. Min Act: -0.1700
Data Index: 2816769 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1635. Min Act: -0.1700
Data Index: 1820834 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1948. Min Act: -0.1700
Data Index: 1201676 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1635. Min Act: -0.1700
Data Index: 1272331 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1635. Min Act: -0.1700
Data Index: 3332162 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1635. Min Act: -0.1700
Data Index: 2190438 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1323. Min Act: -0.1700
Data Index: 2028575 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1323. Min Act: -0.1700
Data Index: 621706 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1323. Min Act: -0.1700
Data Index: 3652085 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1635. Min Act: -0.1700
Data Index: 2896294 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4760. Min Range: -4.4760
Max Act: 4.1323. Min Act: -0.1700
Data Index: 624993 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19