Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.4998. Min Act: -0.1700
Data Index: 952787 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.4373. Min Act: -0.1700
Data Index: 4878644 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.4060. Min Act: -0.1700
Data Index: 702792 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.3748. Min Act: -0.1700
Data Index: 4648054 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.2810. Min Act: -0.1700
Data Index: 8482612 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.2498. Min Act: -0.1700
Data Index: 8003365 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.2185. Min Act: -0.1700
Data Index: 2819336 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.2185. Min Act: -0.1700
Data Index: 2421687 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.2498. Min Act: -0.1700
Data Index: 1115824 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1560. Min Act: -0.1700
Data Index: 4049236 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7415946 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7698915 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1248. Min Act: -0.1700
Data Index: 949537 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1248. Min Act: -0.1700
Data Index: 3604335 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.1248. Min Act: -0.1700
Data Index: 8045056 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.0623. Min Act: -0.1700
Data Index: 610425 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1951967 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.0310. Min Act: -0.1700
Data Index: 7841856 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4998. Min Range: -7.4998
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1600338 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4998. Min Range: -7.4998
Max Act: 6.9998. Min Act: -0.1700
Data Index: 847813 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19