Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6795. Min Act: -0.1700
Data Index: 3765532 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5851153 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.6170. Min Act: -0.1700
Data Index: 6880393 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5857. Min Act: -0.1700
Data Index: 5614249 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5857. Min Act: -0.1700
Data Index: 687548 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5545. Min Act: -0.1700
Data Index: 2411392 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.5857. Min Act: -0.1700
Data Index: 4891662 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7475742 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4607. Min Act: -0.1700
Data Index: 1390442 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4295. Min Act: -0.1700
Data Index: 3332712 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4607. Min Act: -0.1700
Data Index: 5036947 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4295. Min Act: -0.1700
Data Index: 3924727 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.4295. Min Act: -0.1700
Data Index: 2257505 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3451656 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3357. Min Act: -0.1700
Data Index: 6444381 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3357. Min Act: -0.1700
Data Index: 4250474 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3357. Min Act: -0.1700
Data Index: 5869136 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3045. Min Act: -0.1700
Data Index: 5041935 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3357. Min Act: -0.1700
Data Index: 5454267 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6795. Min Range: -6.6795
Max Act: 6.3045. Min Act: -0.1700
Data Index: 4044678 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19