Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5813. Min Act: -0.0001

Data Index: 592391 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5255. Min Act: -0.0001

Data Index: 344050 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5310. Min Act: -0.0002

Data Index: 574970 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5060. Min Act: -0.0001

Data Index: 331952 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5012. Min Act: -0.0002

Data Index: 895647 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4877. Min Act: -0.0001

Data Index: 610438 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4651. Min Act: -0.0001

Data Index: 1169556 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4732. Min Act: -0.0002

Data Index: 211104 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4597. Min Act: -0.0002

Data Index: 394 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4902. Min Act: -0.0001

Data Index: 81169 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4415. Min Act: -0.0002

Data Index: 16151 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4496. Min Act: -0.0002

Data Index: 108093 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4364. Min Act: -0.0002

Data Index: 989265 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4035. Min Act: -0.0001

Data Index: 779710 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4323. Min Act: -0.0001

Data Index: 20365 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4310. Min Act: -0.0002

Data Index: 139818 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4282. Min Act: -0.0002

Data Index: 1288621 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4157. Min Act: -0.0001

Data Index: 655648 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4068. Min Act: -0.0001

Data Index: 351006 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4260. Min Act: -0.0001

Data Index: 502637 (C4 (Web Text))

Max Activating Token Index: 406