Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 351 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.2165. Min Act: -0.1700
Data Index: 6446216 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.0495. Min Act: -0.1700
Data Index: 4993230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.0495. Min Act: -0.1700
Data Index: 7310765 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1276913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.0158. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2165. Min Range: -2.2165
Max Act: 2.0495. Min Act: -0.1700
Data Index: 7218993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9989. Min Act: -0.1700
Data Index: 7219007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9989. Min Act: -0.1700
Data Index: 7219008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9820. Min Act: -0.1700
Data Index: 526933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9820. Min Act: -0.1700
Data Index: 7218987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9820. Min Act: -0.1700
Data Index: 3532521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9989. Min Act: -0.1700
Data Index: 3509488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9651. Min Act: -0.1700
Data Index: 6732063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9651. Min Act: -0.1700
Data Index: 8748857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9651. Min Act: -0.1700
Data Index: 7218997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9481. Min Act: -0.1700
Data Index: 7218988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9311. Min Act: -0.1700
Data Index: 3784743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9311. Min Act: -0.1700
Data Index: 7192422 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9141. Min Act: -0.1699
Data Index: 4649022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2165. Min Range: -2.2165
Max Act: 1.9141. Min Act: -0.1700
Data Index: 7123590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19