Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.5135. Min Act: -0.1700
Data Index: 4934329 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.3260. Min Act: -0.1700
Data Index: 6856513 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.2010. Min Act: -0.1700
Data Index: 1608630 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.1697. Min Act: -0.1700
Data Index: 8237936 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.2010. Min Act: -0.1700
Data Index: 5497910 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5135. Min Range: -6.5135
Max Act: 6.1072. Min Act: -0.1700
Data Index: 5050105 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.9197. Min Act: -0.1700
Data Index: 3602871 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.9510. Min Act: -0.1700
Data Index: 1266134 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.9510. Min Act: -0.1700
Data Index: 2131928 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7947. Min Act: -0.1700
Data Index: 5823651 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7947. Min Act: -0.1700
Data Index: 3811054 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7947. Min Act: -0.1700
Data Index: 5856404 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1200105 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.6697. Min Act: -0.1700
Data Index: 1429173 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2193176 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 5857076 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 7856973 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 8200818 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 6582480 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5135. Min Range: -6.5135
Max Act: 5.7010. Min Act: -0.1700
Data Index: 6116239 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19