Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5150 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 2205781 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 1593233 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 2519868 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 7857024 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.7074. Min Act: -0.1700
Data Index: 1630630 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5824. Min Act: -0.1700
Data Index: 5836165 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5511. Min Act: -0.1700
Data Index: 7472333 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.5199. Min Act: -0.1700
Data Index: 2519870 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4574. Min Act: -0.1700
Data Index: 4594537 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4886. Min Act: -0.1700
Data Index: 346294 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4574. Min Act: -0.1700
Data Index: 2045388 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4886. Min Act: -0.1700
Data Index: 4070482 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4261. Min Act: -0.1700
Data Index: 8143285 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4261. Min Act: -0.1700
Data Index: 8116652 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.3949. Min Act: -0.1700
Data Index: 6970000 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.3949. Min Act: -0.1700
Data Index: 1761637 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.3949. Min Act: -0.1700
Data Index: 6127410 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.4261. Min Act: -0.1700
Data Index: 1568365 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.3636. Min Act: -0.1700
Data Index: 5745253 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.3636. Min Act: -0.1700
Data Index: 4581694 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19