Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7825. Min Act: -0.0000

Data Index: 249136 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7612. Min Act: -0.0000

Data Index: 90071 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7350. Min Act: -0.0000

Data Index: 342378 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7341. Min Act: -0.0000

Data Index: 591933 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7237. Min Act: -0.0000

Data Index: 8420 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6925. Min Act: 0.0001

Data Index: 265016 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6954. Min Act: -0.0000

Data Index: 193753 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6873. Min Act: -0.0000

Data Index: 887145 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6559. Min Act: -0.0000

Data Index: 583603 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6803. Min Act: -0.0000

Data Index: 147199 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6557. Min Act: 0.0001

Data Index: 494552 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6723. Min Act: -0.0000

Data Index: 986108 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6698. Min Act: 0.0000

Data Index: 1200242 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1305543 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6233. Min Act: -0.0000

Data Index: 478729 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1085864 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6190. Min Act: -0.0000

Data Index: 364543 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6588. Min Act: -0.0000

Data Index: 879047 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6459. Min Act: 0.0000

Data Index: 176322 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1290473 (C4 (Web Text))

Max Activating Token Index: 642