Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.4714. Min Act: -0.1700
Data Index: 5260206 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.4089. Min Act: -0.1700
Data Index: 7985764 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4714. Min Range: -8.4714
Max Act: 8.1589. Min Act: -0.1700
Data Index: 2005051 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.9714. Min Act: -0.1700
Data Index: 6195461 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 5063915 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 7467114 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 3838276 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5964. Min Act: -0.1700
Data Index: 1812069 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5964. Min Act: -0.1700
Data Index: 2652880 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5964. Min Act: -0.1700
Data Index: 5833504 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 6804564 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 6676524 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4401. Min Act: -0.1700
Data Index: 7785423 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.4089. Min Act: -0.1700
Data Index: 146770 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.3776. Min Act: -0.1700
Data Index: 7141303 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.3776. Min Act: -0.1700
Data Index: 4200612 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.3464. Min Act: -0.1700
Data Index: 7485236 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.3464. Min Act: -0.1700
Data Index: 2753574 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.2839. Min Act: -0.1700
Data Index: 8297268 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4714. Min Range: -8.4714
Max Act: 7.3151. Min Act: -0.1700
Data Index: 4979651 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19