Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.7687. Min Act: -0.1700
Data Index: 8195437 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.6749. Min Act: -0.1700
Data Index: 8008434 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.6124. Min Act: -0.1700
Data Index: 6641874 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2583527 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.6124. Min Act: -0.1700
Data Index: 7451878 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.6124. Min Act: -0.1700
Data Index: 8499922 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.5499. Min Act: -0.1700
Data Index: 8496900 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.5812. Min Act: -0.1700
Data Index: 668614 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.4874. Min Act: -0.1700
Data Index: 3597655 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.4249. Min Act: -0.1700
Data Index: 2939347 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3937. Min Act: -0.1700
Data Index: 172836 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3624. Min Act: -0.1700
Data Index: 8417578 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3937. Min Act: -0.1700
Data Index: 6783905 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3624. Min Act: -0.1700
Data Index: 4360994 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3624. Min Act: -0.1700
Data Index: 3707208 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.3312. Min Act: -0.1700
Data Index: 969328 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.2999. Min Act: -0.1700
Data Index: 4032557 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.2999. Min Act: -0.1700
Data Index: 5015494 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.2999. Min Act: -0.1700
Data Index: 302980 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7687. Min Range: -6.7687
Max Act: 6.2687. Min Act: -0.1700
Data Index: 403080 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19