Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.7891. Min Act: -0.1700
Data Index: 887894 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6954. Min Act: -0.1700
Data Index: 8553303 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6641. Min Act: -0.1700
Data Index: 2205444 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6954. Min Act: -0.1700
Data Index: 7224501 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6641. Min Act: -0.1700
Data Index: 5279719 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6016. Min Act: -0.1700
Data Index: 1573447 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6329. Min Act: -0.1700
Data Index: 2156887 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6016. Min Act: -0.1700
Data Index: 5507795 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.6016. Min Act: -0.1700
Data Index: 5414922 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.5704. Min Act: -0.1700
Data Index: 1373531 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4766. Min Act: -0.1700
Data Index: 6975557 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.5079. Min Act: -0.1700
Data Index: 6379863 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4454. Min Act: -0.1700
Data Index: 3781651 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4454. Min Act: -0.1700
Data Index: 6856137 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4454. Min Act: -0.1700
Data Index: 3954458 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4766. Min Act: -0.1700
Data Index: 51368 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4454. Min Act: -0.1700
Data Index: 5808683 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4454. Min Act: -0.1700
Data Index: 3317559 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4141. Min Act: -0.1700
Data Index: 5893066 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7891. Min Range: -6.7891
Max Act: 6.4141. Min Act: -0.1700
Data Index: 6890610 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19