Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0954. Min Range: -8.0954
Max Act: 8.0954. Min Act: -0.1700
Data Index: 1441996 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.9704. Min Act: -0.1700
Data Index: 6676907 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.6579. Min Act: -0.1700
Data Index: 1157883 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.5954. Min Act: -0.1700
Data Index: 2025702 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.5954. Min Act: -0.1700
Data Index: 6124261 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.5954. Min Act: -0.1700
Data Index: 3665194 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.5329. Min Act: -0.1700
Data Index: 3529385 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.5329. Min Act: -0.1700
Data Index: 7630727 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4704. Min Act: -0.1700
Data Index: 549057 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4704. Min Act: -0.1700
Data Index: 95416 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4392. Min Act: -0.1700
Data Index: 2599091 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4079. Min Act: -0.1700
Data Index: 4886226 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4079. Min Act: -0.1700
Data Index: 5851160 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4079. Min Act: -0.1700
Data Index: 3378091 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.4079. Min Act: -0.1700
Data Index: 6554582 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.3767. Min Act: -0.1700
Data Index: 2490585 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.3767. Min Act: -0.1700
Data Index: 6255341 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.3767. Min Act: -0.1700
Data Index: 5477084 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.3767. Min Act: -0.1700
Data Index: 1602878 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0954. Min Range: -8.0954
Max Act: 7.3142. Min Act: -0.1700
Data Index: 3551466 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19