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

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

Neuron 779 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1321172 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1087115 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0376. Min Act: -0.0002

Data Index: 903743 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0347. Min Act: -0.0002

Data Index: 207058 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0374. Min Act: -0.0002

Data Index: 718126 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1046352 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1130603 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1263711 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0344. Min Act: -0.0002

Data Index: 401510 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0345. Min Act: -0.0002

Data Index: 714361 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0328. Min Act: -0.0002

Data Index: 450187 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0336. Min Act: -0.0001

Data Index: 229115 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0341. Min Act: -0.0002

Data Index: 416158 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0335. Min Act: -0.0002

Data Index: 581543 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0335. Min Act: -0.0002

Data Index: 570844 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0330. Min Act: -0.0002

Data Index: 155875 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1035675 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0327. Min Act: -0.0001

Data Index: 753157 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0328. Min Act: -0.0002

Data Index: 155970 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0312. Min Act: -0.0002

Data Index: 180610 (C4 (Web Text))

Max Activating Token Index: 630