Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.7872. Min Act: -0.1700
Data Index: 3910800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.7441. Min Act: -0.1700
Data Index: 2038739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6834. Min Act: -0.1699
Data Index: 4176291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6748. Min Act: -0.1700
Data Index: 155039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6661. Min Act: -0.1700
Data Index: 4357571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6574. Min Act: -0.1700
Data Index: 4406545 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6574. Min Act: -0.1700
Data Index: 3861680 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6313. Min Act: -0.1700
Data Index: 2270684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6313. Min Act: -0.1700
Data Index: 3833183 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6225. Min Act: -0.1700
Data Index: 315913 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6225. Min Act: -0.1700
Data Index: 1195837 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6225. Min Act: -0.1700
Data Index: 5311601 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6225. Min Act: -0.1549
Data Index: 6097219 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6138. Min Act: -0.1700
Data Index: 3295775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6138. Min Act: -0.1700
Data Index: 4276851 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6051. Min Act: -0.1700
Data Index: 7109761 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6051. Min Act: -0.1700
Data Index: 4239142 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6138. Min Act: -0.1700
Data Index: 1783514 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6138. Min Act: -0.1700
Data Index: 473556 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7872. Min Range: -1.7872
Max Act: 1.6138. Min Act: -0.1670
Data Index: 2485400 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19