Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1600 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.3854. Min Act: -0.1700
Data Index: 312517 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.3527. Min Act: -0.1700
Data Index: 852208 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2871. Min Act: -0.1698
Data Index: 1051986 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.3035. Min Act: -0.1700
Data Index: 288595 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2706. Min Act: -0.1700
Data Index: 1119821 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2871. Min Act: -0.1700
Data Index: 1154561 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2706. Min Act: -0.1700
Data Index: 1187681 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2541. Min Act: -0.1700
Data Index: 149272 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2376. Min Act: -0.1700
Data Index: 28210 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2376. Min Act: -0.1700
Data Index: 74359 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2211. Min Act: -0.1700
Data Index: 591160 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2211. Min Act: -0.1700
Data Index: 627642 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2045. Min Act: -0.1699
Data Index: 769898 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2045. Min Act: -0.1700
Data Index: 13991 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.2045. Min Act: -0.1700
Data Index: 1044397 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.1713. Min Act: -0.1700
Data Index: 692280 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.1713. Min Act: -0.1700
Data Index: 1089061 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.1380. Min Act: -0.1700
Data Index: 75531 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.1380. Min Act: -0.1700
Data Index: 48366 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3854. Min Range: -2.3854
Max Act: 2.1380. Min Act: -0.1700
Data Index: 643489 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19