Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8663. Min Act: -0.1700
Data Index: 6057874 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 8085906 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 3246272 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 6196376 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 7475104 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 4697069 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 2815469 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 5467398 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 6759110 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1969014 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 6531750 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 6422521 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 3950696 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 1573260 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 333271 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 6032127 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 8679789 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6475. Min Act: -0.1700
Data Index: 6411062 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6475. Min Act: -0.1700
Data Index: 2216302 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.6475. Min Act: -0.1700
Data Index: 3510095 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19