Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 205 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.5332. Min Act: -0.1700
Data Index: 5833455 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.3608. Min Act: -0.1700
Data Index: 6557125 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.2510. Min Act: -0.1700
Data Index: 4112126 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.2195. Min Act: -0.1700
Data Index: 3281515 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.2038. Min Act: -0.1700
Data Index: 6604503 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1881. Min Act: -0.1700
Data Index: 1228473 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1881. Min Act: -0.1700
Data Index: 5746673 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 5764192 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 8581046 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 5999407 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 5062710 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1881. Min Act: -0.1700
Data Index: 6919586 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 600491 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1723. Min Act: -0.1700
Data Index: 5222734 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1566. Min Act: -0.1700
Data Index: 4412536 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1409. Min Act: -0.1700
Data Index: 6246916 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1566. Min Act: -0.1700
Data Index: 4909350 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1566. Min Act: -0.1700
Data Index: 3651338 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1409. Min Act: -0.1700
Data Index: 3616155 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5332. Min Range: -3.5332
Max Act: 3.1409. Min Act: -0.1700
Data Index: 6925826 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19