Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.4904. Min Act: -0.1700
Data Index: 971588 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.5529. Min Act: -0.1700
Data Index: 3360625 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3654. Min Act: -0.1700
Data Index: 4911150 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3654. Min Act: -0.1700
Data Index: 254301 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3654. Min Act: -0.1700
Data Index: 1513191 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3029. Min Act: -0.1700
Data Index: 2873987 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3029. Min Act: -0.1700
Data Index: 7833214 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.3029. Min Act: -0.1700
Data Index: 400590 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.1779. Min Act: -0.1700
Data Index: 7593300 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.1779. Min Act: -0.1700
Data Index: 7550916 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.1154. Min Act: -0.1700
Data Index: 7415134 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.1154. Min Act: -0.1700
Data Index: 6103461 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.1154. Min Act: -0.1700
Data Index: 7039861 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.0529. Min Act: -0.1700
Data Index: 3503581 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5529. Min Range: -9.5529
Max Act: 9.0529. Min Act: -0.1700
Data Index: 3208252 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5529. Min Range: -9.5529
Max Act: 8.9904. Min Act: -0.1700
Data Index: 3945210 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5529. Min Range: -9.5529
Max Act: 8.9904. Min Act: -0.1700
Data Index: 4826212 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5529. Min Range: -9.5529
Max Act: 8.9904. Min Act: -0.1700
Data Index: 668913 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5529. Min Range: -9.5529
Max Act: 8.9279. Min Act: -0.1700
Data Index: 265385 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5529. Min Range: -9.5529
Max Act: 8.9279. Min Act: -0.1700
Data Index: 133109 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19