Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0509. Min Act: -0.0002

Data Index: 894347 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1017085 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1130400 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1299592 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0441. Min Act: -0.0001

Data Index: 444392 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1242297 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0438. Min Act: -0.0001

Data Index: 169085 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0414. Min Act: -0.0001

Data Index: 997230 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0445. Min Act: -0.0002

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0423. Min Act: -0.0001

Data Index: 541900 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0421. Min Act: -0.0001

Data Index: 879156 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0001

Data Index: 156896 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1146498 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0383. Min Act: -0.0001

Data Index: 368153 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1265074 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0374. Min Act: -0.0001

Data Index: 903856 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0361. Min Act: -0.0001

Data Index: 900470 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0337. Min Act: -0.0001

Data Index: 30225 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1236733 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0362. Min Act: -0.0001

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 677