Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.7359. Min Act: -0.1700
Data Index: 5668574 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.6422. Min Act: -0.1700
Data Index: 1627677 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.6422. Min Act: -0.1700
Data Index: 8623937 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.6734. Min Act: -0.1700
Data Index: 1916292 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.5484. Min Act: -0.1700
Data Index: 1277547 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.5172. Min Act: -0.1700
Data Index: 3035414 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.5172. Min Act: -0.1700
Data Index: 7879013 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.5172. Min Act: -0.1700
Data Index: 4871383 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4859. Min Act: -0.1700
Data Index: 6999530 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4547. Min Act: -0.1700
Data Index: 1074381 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4547. Min Act: -0.1700
Data Index: 1085126 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4234. Min Act: -0.1700
Data Index: 5026039 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4234. Min Act: -0.1700
Data Index: 2790445 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.3922. Min Act: -0.1700
Data Index: 8048357 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.4234. Min Act: -0.1700
Data Index: 4587329 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.3922. Min Act: -0.1700
Data Index: 3088288 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.3922. Min Act: -0.1700
Data Index: 338209 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.3297. Min Act: -0.1700
Data Index: 1641312 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.3297. Min Act: -0.1700
Data Index: 71769 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7359. Min Range: -4.7359
Max Act: 4.2984. Min Act: -0.1700
Data Index: 648079 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19