Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4454 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2014. Min Range: -8.2014
Max Act: 8.2014. Min Act: -0.1700
Data Index: 8618896 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.8577. Min Act: -0.1700
Data Index: 7963089 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7952. Min Act: -0.1700
Data Index: 870707 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7639. Min Act: -0.1700
Data Index: 5009534 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7952. Min Act: -0.1700
Data Index: 516126 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7014. Min Act: -0.1700
Data Index: 411967 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7327. Min Act: -0.1700
Data Index: 4897237 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.7014. Min Act: -0.1700
Data Index: 1925518 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.6702. Min Act: -0.1700
Data Index: 2195471 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.6702. Min Act: -0.1700
Data Index: 6489495 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.6702. Min Act: -0.1700
Data Index: 6835113 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.6389. Min Act: -0.1700
Data Index: 1519242 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.5764. Min Act: -0.1700
Data Index: 3168638 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.5764. Min Act: -0.1700
Data Index: 329714 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.5139. Min Act: -0.1700
Data Index: 7391745 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.5139. Min Act: -0.1700
Data Index: 8536636 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.4514. Min Act: -0.1700
Data Index: 4812289 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.4827. Min Act: -0.1700
Data Index: 6241244 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.4514. Min Act: -0.1700
Data Index: 5225307 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2014. Min Range: -8.2014
Max Act: 7.4202. Min Act: -0.1700
Data Index: 2714575 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19