Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.6714. Min Act: -0.1700
Data Index: 2972271 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.3901. Min Act: -0.1700
Data Index: 5837129 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2964. Min Act: -0.1700
Data Index: 3215790 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.3276. Min Act: -0.1700
Data Index: 3380737 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2964. Min Act: -0.1700
Data Index: 2400450 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 7489000 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 103769 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 7488989 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 7488990 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1182502 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 6987262 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 4496737 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2339. Min Act: -0.1700
Data Index: 7214123 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2026. Min Act: -0.1700
Data Index: 7432158 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.1714. Min Act: -0.1700
Data Index: 3453191 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.1714. Min Act: -0.1700
Data Index: 950489 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.1401. Min Act: -0.1700
Data Index: 7214116 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2026. Min Act: -0.1700
Data Index: 1118723 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.1714. Min Act: -0.1700
Data Index: 1991875 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6714. Min Range: -5.6714
Max Act: 5.2026. Min Act: -0.1700
Data Index: 3481629 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19