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

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

Neuron 5454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.9695. Min Act: -0.0000

Data Index: 777023 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.9163. Min Act: -0.0000

Data Index: 87562 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 4.0443. Min Range: -4.0443

Max Act: 4.0443. Min Act: -0.0000

Data Index: 1171614 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.7159. Min Act: -0.0000

Data Index: 858197 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.5603. Min Act: -0.0000

Data Index: 99898 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.3227. Min Act: -0.0000

Data Index: 1340332 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2239. Min Act: -0.0000

Data Index: 1255931 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2650. Min Act: -0.0000

Data Index: 440525 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2349. Min Act: -0.0000

Data Index: 605559 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2404. Min Act: -0.0000

Data Index: 28583 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2041. Min Act: -0.0000

Data Index: 258119 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.0053. Min Act: -0.0000

Data Index: 875760 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2591. Min Act: -0.0000

Data Index: 775227 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.2496. Min Act: -0.0000

Data Index: 164341 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 4.0443. Min Range: -4.0443

Max Act: 3.0630. Min Act: -0.0000

Data Index: 623517 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 4.0443. Min Range: -4.0443

Max Act: 2.7595. Min Act: -0.0000

Data Index: 805376 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 4.0443. Min Range: -4.0443

Max Act: 2.8783. Min Act: -0.0000

Data Index: 1104181 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 4.0443. Min Range: -4.0443

Max Act: 2.8204. Min Act: -0.0000

Data Index: 251508 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 4.0443. Min Range: -4.0443

Max Act: 2.8125. Min Act: -0.0000

Data Index: 954746 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 4.0443. Min Range: -4.0443

Max Act: 2.9029. Min Act: -0.0000

Data Index: 1057338 (C4 (Web Text))

Max Activating Token Index: 639