Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4960 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.2769. Min Act: -0.1700
Data Index: 1228243 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.2457. Min Act: -0.1700
Data Index: 7053973 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.2144. Min Act: -0.1700
Data Index: 5416972 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.2144. Min Act: -0.1700
Data Index: 2401677 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.1519. Min Act: -0.1700
Data Index: 4631671 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.0582. Min Act: -0.1700
Data Index: 6759476 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.0894. Min Act: -0.1700
Data Index: 716719 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9957. Min Act: -0.1700
Data Index: 4942086 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2769. Min Range: -6.2769
Max Act: 6.0269. Min Act: -0.1700
Data Index: 3523454 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9957. Min Act: -0.1700
Data Index: 7266055 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9957. Min Act: -0.1700
Data Index: 2691618 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1282457 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9644. Min Act: -0.1700
Data Index: 7677342 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9644. Min Act: -0.1700
Data Index: 5292163 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9644. Min Act: -0.1700
Data Index: 5665902 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9332. Min Act: -0.1700
Data Index: 549437 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9019. Min Act: -0.1700
Data Index: 2082915 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.9019. Min Act: -0.1700
Data Index: 6701756 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.8707. Min Act: -0.1700
Data Index: 993170 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2769. Min Range: -6.2769
Max Act: 5.8394. Min Act: -0.1700
Data Index: 8606928 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19