Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.8448. Min Act: -0.1700
Data Index: 4414618 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.5323. Min Act: -0.1700
Data Index: 5339567 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.5323. Min Act: -0.1700
Data Index: 2602307 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.5323. Min Act: -0.1700
Data Index: 7197497 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.5010. Min Act: -0.1700
Data Index: 5253156 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.4698. Min Act: -0.1700
Data Index: 6546337 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.4698. Min Act: -0.1700
Data Index: 4526239 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.4698. Min Act: -0.1700
Data Index: 900338 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.3760. Min Act: -0.1700
Data Index: 3494627 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.3135. Min Act: -0.1700
Data Index: 2962110 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.3135. Min Act: -0.1700
Data Index: 206142 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.3135. Min Act: -0.1700
Data Index: 2347149 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.3448. Min Act: -0.1700
Data Index: 2975401 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 799665 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 7207584 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 3884712 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 5598081 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 5969915 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2510. Min Act: -0.1700
Data Index: 4203556 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8448. Min Range: -6.8448
Max Act: 6.2510. Min Act: -0.1700
Data Index: 2779786 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19