Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 136 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4655. Min Act: -0.0005

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4475. Min Act: -0.0005

Data Index: 295932 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4265. Min Act: -0.0005

Data Index: 1187283 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.4207. Min Act: -0.0005

Data Index: 113780 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3966. Min Act: -0.0005

Data Index: 285440 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3776. Min Act: -0.0005

Data Index: 827227 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3759. Min Act: -0.0005

Data Index: 1358512 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3683. Min Act: -0.0005

Data Index: 495393 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3747. Min Act: -0.0005

Data Index: 376250 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3610. Min Act: -0.0005

Data Index: 103127 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3672. Min Act: -0.0005

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3487. Min Act: -0.0005

Data Index: 397003 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3469. Min Act: -0.0005

Data Index: 279052 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3452. Min Act: -0.0005

Data Index: 480287 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3356. Min Act: -0.0005

Data Index: 1070426 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3342. Min Act: -0.0005

Data Index: 1192341 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3333. Min Act: -0.0005

Data Index: 974526 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3278. Min Act: -0.0005

Data Index: 48894 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3166. Min Act: -0.0005

Data Index: 290674 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.4655. Min Range: -0.4655

Max Act: 0.3054. Min Act: -0.0005

Data Index: 438974 (C4 (Web Text))

Max Activating Token Index: 787