Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4168143 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.5255. Min Act: -0.1700
Data Index: 4168137 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4117018 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4229590 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4229579 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1817. Min Act: -0.1700
Data Index: 8415440 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1817. Min Act: -0.1700
Data Index: 4168147 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1817. Min Act: -0.1700
Data Index: 8415446 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4168141 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4229595 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4168144 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0880. Min Act: -0.1700
Data Index: 4168149 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0880. Min Act: -0.1700
Data Index: 8415447 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.1192. Min Act: -0.1700
Data Index: 2282855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 7531985 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 4229583 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 3750938 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 8415441 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0255. Min Act: -0.1700
Data Index: 4168146 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5567. Min Range: -5.5567
Max Act: 5.0255. Min Act: -0.1700
Data Index: 256817 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19