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

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

Neuron 4211 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.3440. Min Range: -10.3440

Max Act: 10.3440. Min Act: -0.0000

Data Index: 1186488 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 10.3440. Min Range: -10.3440

Max Act: 9.7240. Min Act: -0.0000

Data Index: 217186 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 10.3440. Min Range: -10.3440

Max Act: 9.4513. Min Act: -0.0000

Data Index: 941580 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 10.3440. Min Range: -10.3440

Max Act: 8.6884. Min Act: -0.0000

Data Index: 948645 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 10.3440. Min Range: -10.3440

Max Act: 8.0666. Min Act: -0.0000

Data Index: 587814 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 10.3440. Min Range: -10.3440

Max Act: 6.8075. Min Act: -0.0000

Data Index: 1066032 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 10.3440. Min Range: -10.3440

Max Act: 6.7483. Min Act: -0.0000

Data Index: 15118 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 10.3440. Min Range: -10.3440

Max Act: 5.4480. Min Act: 0.0000

Data Index: 559966 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 10.3440. Min Range: -10.3440

Max Act: 5.5818. Min Act: -0.0000

Data Index: 576636 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 10.3440. Min Range: -10.3440

Max Act: 5.4522. Min Act: -0.0000

Data Index: 791659 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.8838. Min Act: -0.0000

Data Index: 1168160 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.4214. Min Act: -0.0000

Data Index: 1123089 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.4467. Min Act: 0.0000

Data Index: 841208 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.5025. Min Act: -0.0000

Data Index: 72346 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.4678. Min Act: -0.0000

Data Index: 830208 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.0995. Min Act: -0.0000

Data Index: 636205 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 10.3440. Min Range: -10.3440

Max Act: 4.0593. Min Act: -0.0000

Data Index: 1121445 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 10.3440. Min Range: -10.3440

Max Act: 3.9952. Min Act: -0.0000

Data Index: 1273452 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 10.3440. Min Range: -10.3440

Max Act: 3.9853. Min Act: -0.0000

Data Index: 863372 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 10.3440. Min Range: -10.3440

Max Act: 3.8981. Min Act: -0.0000

Data Index: 931058 (C4 (Web Text))

Max Activating Token Index: 631