Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.9110. Min Act: -0.1700
Data Index: 6681295 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8793. Min Act: -0.1700
Data Index: 502889 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8793. Min Act: -0.1700
Data Index: 4889251 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8634. Min Act: -0.1700
Data Index: 5343886 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8634. Min Act: -0.1700
Data Index: 1339365 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8316. Min Act: -0.1700
Data Index: 4973866 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8475. Min Act: -0.1700
Data Index: 1537266 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8475. Min Act: -0.1700
Data Index: 3365729 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7998. Min Act: -0.1700
Data Index: 38706 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.8157. Min Act: -0.1700
Data Index: 4146448 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7998. Min Act: -0.1700
Data Index: 8461165 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7998. Min Act: -0.1700
Data Index: 3665059 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7839. Min Act: -0.1700
Data Index: 4269825 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7839. Min Act: -0.1700
Data Index: 3367391 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7520. Min Act: -0.1700
Data Index: 379442 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7360. Min Act: -0.1700
Data Index: 5587728 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7360. Min Act: -0.1700
Data Index: 5089765 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1176475 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7520. Min Act: -0.1700
Data Index: 4364693 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9110. Min Range: -2.9110
Max Act: 2.7040. Min Act: -0.1700
Data Index: 5064808 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19