Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1351. Min Range: -5.1351
Max Act: 5.1351. Min Act: -0.1700
Data Index: 2540731 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5300040 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.9476. Min Act: -0.1700
Data Index: 199221 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.8851. Min Act: -0.1700
Data Index: 389900 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.8539. Min Act: -0.1700
Data Index: 8437261 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.8539. Min Act: -0.1700
Data Index: 500775 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.8539. Min Act: -0.1700
Data Index: 5300039 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.8226. Min Act: -0.1700
Data Index: 259049 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2334836 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7601. Min Act: -0.1700
Data Index: 2305295 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7914. Min Act: -0.1700
Data Index: 8579566 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2076735 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7601. Min Act: -0.1700
Data Index: 6568213 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7289. Min Act: -0.1700
Data Index: 5359164 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7601. Min Act: -0.1700
Data Index: 6594436 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.6976. Min Act: -0.1700
Data Index: 5587361 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4515714 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7289. Min Act: -0.1700
Data Index: 7207131 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7289. Min Act: -0.1700
Data Index: 500774 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1351. Min Range: -5.1351
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4098325 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19