Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3467. Min Range: -7.3467
Max Act: 7.3467. Min Act: -0.1700
Data Index: 6165670 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3467. Min Range: -7.3467
Max Act: 7.0655. Min Act: -0.1700
Data Index: 3619366 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3467. Min Range: -7.3467
Max Act: 7.0342. Min Act: -0.1700
Data Index: 1698582 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.9717. Min Act: -0.1700
Data Index: 4786207 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.7842. Min Act: -0.1700
Data Index: 3158043 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.6592. Min Act: -0.1700
Data Index: 2349108 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.6280. Min Act: -0.1700
Data Index: 7106285 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 2492925 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 8762375 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.6592. Min Act: -0.1700
Data Index: 2709443 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.6280. Min Act: -0.1700
Data Index: 1648919 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 16069 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 4235659 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 746714 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5967. Min Act: -0.1700
Data Index: 1220587 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5655. Min Act: -0.1700
Data Index: 6497340 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5655. Min Act: -0.1700
Data Index: 250244 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.5030. Min Act: -0.1700
Data Index: 3840054 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.4717. Min Act: -0.1700
Data Index: 6081946 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3467. Min Range: -7.3467
Max Act: 6.4405. Min Act: -0.1700
Data Index: 7024993 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19