Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6214 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.5734. Min Act: -0.1700
Data Index: 3509005 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.5421. Min Act: -0.1700
Data Index: 706474 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.4796. Min Act: -0.1700
Data Index: 1885547 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.4484. Min Act: -0.1700
Data Index: 7840456 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.3859. Min Act: -0.1700
Data Index: 4785548 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.3546. Min Act: -0.1700
Data Index: 8014495 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.3546. Min Act: -0.1700
Data Index: 462856 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.3546. Min Act: -0.1700
Data Index: 8764283 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.3234. Min Act: -0.1700
Data Index: 3482535 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2921. Min Act: -0.1700
Data Index: 5585613 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2921. Min Act: -0.1700
Data Index: 7203172 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2921. Min Act: -0.1700
Data Index: 4578237 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2609. Min Act: -0.1700
Data Index: 7054143 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2609. Min Act: -0.1700
Data Index: 4039923 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2609. Min Act: -0.1700
Data Index: 1278408 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2296. Min Act: -0.1700
Data Index: 8014250 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2296. Min Act: -0.1700
Data Index: 6850726 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.2296. Min Act: -0.1700
Data Index: 8182748 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.1671. Min Act: -0.1700
Data Index: 4437650 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5734. Min Range: -5.5734
Max Act: 5.1984. Min Act: -0.1700
Data Index: 3736360 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19