Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1791 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4635170 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.9232. Min Act: -0.1700
Data Index: 3573022 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8920. Min Act: -0.1700
Data Index: 2953897 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8920. Min Act: -0.1700
Data Index: 5615786 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8920. Min Act: -0.1700
Data Index: 2046667 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8920. Min Act: -0.1700
Data Index: 1128151 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8607. Min Act: -0.1700
Data Index: 798928 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8607. Min Act: -0.1700
Data Index: 1718047 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.8295. Min Act: -0.1700
Data Index: 4540704 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5326729 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5229522 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7670. Min Act: -0.1700
Data Index: 4326447 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7982. Min Act: -0.1700
Data Index: 27246 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5946088 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7670. Min Act: -0.1700
Data Index: 8494642 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7670. Min Act: -0.1700
Data Index: 5418135 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7670. Min Act: -0.1700
Data Index: 1191367 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7670. Min Act: -0.1700
Data Index: 1170508 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7357. Min Act: -0.1700
Data Index: 3597826 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9232. Min Range: -4.9232
Max Act: 4.7357. Min Act: -0.1700
Data Index: 5205619 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19