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

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

Neuron 5279 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: 2.4702. Min Range: -2.4702

Max Act: 2.4702. Min Act: -0.0000

Data Index: 578286 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 2.4702. Min Range: -2.4702

Max Act: 2.1941. Min Act: -0.0000

Data Index: 348652 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 2.4702. Min Range: -2.4702

Max Act: 2.0437. Min Act: -0.0000

Data Index: 1304316 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 2.4702. Min Range: -2.4702

Max Act: 2.1043. Min Act: 0.0000

Data Index: 954862 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 2.4702. Min Range: -2.4702

Max Act: 2.0519. Min Act: -0.0000

Data Index: 1128309 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 2.4702. Min Range: -2.4702

Max Act: 2.0236. Min Act: -0.0000

Data Index: 320399 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.9955. Min Act: 0.0000

Data Index: 502202 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8896. Min Act: 0.0000

Data Index: 180222 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8927. Min Act: 0.0000

Data Index: 981737 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1080303 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.7850. Min Act: 0.0000

Data Index: 77435 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8714. Min Act: -0.0000

Data Index: 693254 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8574. Min Act: -0.0000

Data Index: 686989 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1561552 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.8410. Min Act: -0.0000

Data Index: 758267 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.6686. Min Act: -0.0000

Data Index: 1073738 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.6385. Min Act: -0.0000

Data Index: 328919 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.7379. Min Act: -0.0000

Data Index: 652392 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.7268. Min Act: 0.0001

Data Index: 1153691 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 2.4702. Min Range: -2.4702

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1108111 (C4 (Web Text))

Max Activating Token Index: 396