Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2539. Min Range: -8.2539
Max Act: 8.2539. Min Act: -0.1700
Data Index: 4431694 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2539. Min Range: -8.2539
Max Act: 8.0664. Min Act: -0.1700
Data Index: 2663018 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2539. Min Range: -8.2539
Max Act: 8.0039. Min Act: -0.1700
Data Index: 6937809 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.8476. Min Act: -0.1700
Data Index: 8227745 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7851. Min Act: -0.1700
Data Index: 3961484 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7851. Min Act: -0.1700
Data Index: 1381705 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7539. Min Act: -0.1700
Data Index: 3692689 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7226. Min Act: -0.1700
Data Index: 6285250 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7539. Min Act: -0.1700
Data Index: 5530105 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.7226. Min Act: -0.1700
Data Index: 7352223 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.6289. Min Act: -0.1700
Data Index: 6162331 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.5664. Min Act: -0.1700
Data Index: 5923903 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.5039. Min Act: -0.1700
Data Index: 2691142 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.5351. Min Act: -0.1700
Data Index: 1765121 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.5039. Min Act: -0.1700
Data Index: 7408445 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.5039. Min Act: -0.1700
Data Index: 4558055 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5287782 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.4414. Min Act: -0.1700
Data Index: 6805504 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.4101. Min Act: -0.1700
Data Index: 6435449 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2539. Min Range: -8.2539
Max Act: 7.4101. Min Act: -0.1700
Data Index: 5015587 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19