Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.3142. Min Act: -0.1700
Data Index: 7337883 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.2204. Min Act: -0.1700
Data Index: 8546342 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1892. Min Act: -0.1700
Data Index: 2585183 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1579. Min Act: -0.1700
Data Index: 5745374 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1579. Min Act: -0.1700
Data Index: 6384821 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1267. Min Act: -0.1700
Data Index: 1318530 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1267. Min Act: -0.1700
Data Index: 6743943 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.1267. Min Act: -0.1700
Data Index: 6815908 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0954. Min Act: -0.1700
Data Index: 1069957 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0954. Min Act: -0.1700
Data Index: 2312211 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0954. Min Act: -0.1700
Data Index: 5543588 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0954. Min Act: -0.1700
Data Index: 7264889 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 3453480 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0642. Min Act: -0.1700
Data Index: 5137993 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0642. Min Act: -0.1700
Data Index: 5936548 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 2744102 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 2602594 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4065011 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 7501905 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3142. Min Range: -5.3142
Max Act: 5.0329. Min Act: -0.1700
Data Index: 1440486 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19