Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.8734. Min Act: -0.1700
Data Index: 239836 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.6546. Min Act: -0.1700
Data Index: 6654740 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.6859. Min Act: -0.1700
Data Index: 3630048 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.6234. Min Act: -0.1700
Data Index: 6148624 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.6234. Min Act: -0.1700
Data Index: 8566803 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.5921. Min Act: -0.1700
Data Index: 3279520 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.5921. Min Act: -0.1699
Data Index: 3184954 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4984. Min Act: -0.1700
Data Index: 2589193 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.5296. Min Act: -0.1700
Data Index: 7218293 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3783236 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4671. Min Act: -0.1700
Data Index: 4681460 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4671. Min Act: -0.1700
Data Index: 2609038 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4046. Min Act: -0.1700
Data Index: 2633567 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4359. Min Act: -0.1700
Data Index: 4210662 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.4046. Min Act: -0.1700
Data Index: 4726953 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.3109. Min Act: -0.1700
Data Index: 59481 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.3109. Min Act: -0.1700
Data Index: 8808122 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.2796. Min Act: -0.1700
Data Index: 88575 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.2796. Min Act: -0.1700
Data Index: 4726833 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8734. Min Range: -7.8734
Max Act: 7.2484. Min Act: -0.1700
Data Index: 8351300 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19