Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2181 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1832. Min Act: -0.1700
Data Index: 5258423 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1499. Min Act: -0.1700
Data Index: 3556449 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1332. Min Act: -0.1700
Data Index: 1103722 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1332. Min Act: -0.1700
Data Index: 4011429 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1332. Min Act: -0.1700
Data Index: 6912940 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.1165. Min Act: -0.1700
Data Index: 6025470 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0830. Min Act: -0.1700
Data Index: 5777573 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0998. Min Act: -0.1700
Data Index: 5301340 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0998. Min Act: -0.1700
Data Index: 4704345 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0830. Min Act: -0.1700
Data Index: 2005745 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0830. Min Act: -0.1700
Data Index: 8340055 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0830. Min Act: -0.1700
Data Index: 28358 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0494. Min Act: -0.1700
Data Index: 759334 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0494. Min Act: -0.1700
Data Index: 5831642 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0494. Min Act: -0.1700
Data Index: 1084761 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0326. Min Act: -0.1700
Data Index: 2460928 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0662. Min Act: -0.1700
Data Index: 3716288 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0494. Min Act: -0.1700
Data Index: 2937295 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0326. Min Act: -0.1700
Data Index: 8353218 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1832. Min Range: -2.1832
Max Act: 2.0494. Min Act: -0.1700
Data Index: 8158615 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19