Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.6714. Min Act: -0.1700
Data Index: 5293941 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.6402. Min Act: -0.1700
Data Index: 2309058 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.5777. Min Act: -0.1700
Data Index: 6836264 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.5777. Min Act: -0.1700
Data Index: 4526287 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.5777. Min Act: -0.1700
Data Index: 4029804 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4839. Min Act: -0.1700
Data Index: 6139733 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4839. Min Act: -0.1700
Data Index: 6775613 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4527. Min Act: -0.1700
Data Index: 7275686 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3331913 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3245807 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4214. Min Act: -0.1700
Data Index: 8546078 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3226808 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3682890 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3589. Min Act: -0.1700
Data Index: 3503843 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3277. Min Act: -0.1700
Data Index: 3691436 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3902. Min Act: -0.1700
Data Index: 5040037 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3589. Min Act: -0.1700
Data Index: 3956874 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3589. Min Act: -0.1700
Data Index: 2568474 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3589. Min Act: -0.1700
Data Index: 7158562 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6714. Min Range: -6.6714
Max Act: 6.3277. Min Act: -0.1700
Data Index: 2848239 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19