Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2348 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.1372. Min Act: -0.1700
Data Index: 4107321 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.1372. Min Act: -0.1700
Data Index: 631781 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.0747. Min Act: -0.1700
Data Index: 8564843 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.0435. Min Act: -0.1700
Data Index: 5627494 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.0122. Min Act: -0.1700
Data Index: 5889284 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.0122. Min Act: -0.1700
Data Index: 7575681 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1372. Min Range: -5.1372
Max Act: 5.0122. Min Act: -0.1700
Data Index: 3341008 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.9810. Min Act: -0.1700
Data Index: 2336080 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 782121 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8872. Min Act: -0.1700
Data Index: 2239497 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8872. Min Act: -0.1700
Data Index: 3250146 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8872. Min Act: -0.1700
Data Index: 6832737 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8872. Min Act: -0.1700
Data Index: 503966 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8872. Min Act: -0.1700
Data Index: 5024549 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 7880424 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 6898659 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 5214300 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 7768962 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 3471542 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1372. Min Range: -5.1372
Max Act: 4.8560. Min Act: -0.1700
Data Index: 2362028 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19