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

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

Neuron 1130 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0411. Min Act: -0.0005

Data Index: 1209416 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0005

Data Index: 1203874 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0390. Min Act: -0.0005

Data Index: 460152 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1085652 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0333. Min Act: -0.0005

Data Index: 893856 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1111284 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0346. Min Act: -0.0005

Data Index: 535625 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1069046 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0342. Min Act: -0.0005

Data Index: 246215 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0328. Min Act: -0.0005

Data Index: 855728 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0310. Min Act: -0.0005

Data Index: 1140047 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0345. Min Act: -0.0005

Data Index: 901145 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0314. Min Act: -0.0005

Data Index: 564646 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0331. Min Act: -0.0005

Data Index: 1268071 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0321. Min Act: -0.0005

Data Index: 319679 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0322. Min Act: -0.0005

Data Index: 1240291 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0318. Min Act: -0.0005

Data Index: 1174558 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0315. Min Act: -0.0005

Data Index: 26388 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0321. Min Act: -0.0005

Data Index: 1173165 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0319. Min Act: -0.0005

Data Index: 314692 (C4 (Web Text))

Max Activating Token Index: 68