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

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

Neuron 3327 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: 2.0816. Min Range: -2.0816

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1390441 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.9745. Min Act: -0.0000

Data Index: 774678 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4678. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.2685. Min Act: -0.0000

Data Index: 319595 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.5145. Min Act: -0.0000

Data Index: 1224378 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1263674 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4472. Min Act: -0.0000

Data Index: 764347 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1038875 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.5182. Min Act: -0.0000

Data Index: 497054 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1557018 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4384. Min Act: -0.0000

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4363. Min Act: -0.0000

Data Index: 903558 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4993. Min Act: -0.0000

Data Index: 278221 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1191906 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.3787. Min Act: -0.0000

Data Index: 206441 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.3708. Min Act: -0.0000

Data Index: 639049 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1076078 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.3919. Min Act: -0.0000

Data Index: 473836 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.2418. Min Act: -0.0000

Data Index: 877505 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 2.0816. Min Range: -2.0816

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1163510 (C4 (Web Text))

Max Activating Token Index: 429