Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0510. Min Range: -7.0510
Max Act: 7.0510. Min Act: -0.1700
Data Index: 2429003 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.9885. Min Act: -0.1700
Data Index: 2548303 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.9572. Min Act: -0.1700
Data Index: 6758022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.9260. Min Act: -0.1700
Data Index: 7016509 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.8947. Min Act: -0.1700
Data Index: 7214079 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.8010. Min Act: -0.1700
Data Index: 6635991 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.7697. Min Act: -0.1700
Data Index: 5923362 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.7072. Min Act: -0.1700
Data Index: 7253461 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1801121 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.6760. Min Act: -0.1700
Data Index: 4603295 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.6760. Min Act: -0.1700
Data Index: 1010340 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.6447. Min Act: -0.1700
Data Index: 486136 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5822. Min Act: -0.1700
Data Index: 486130 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 6477653 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 1647904 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 6256787 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 2073399 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 973191 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5197. Min Act: -0.1700
Data Index: 7098515 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0510. Min Range: -7.0510
Max Act: 6.5197. Min Act: -0.1700
Data Index: 744284 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19