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

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

Neuron 4044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4334. Min Act: -0.0001

Data Index: 1287582 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4784. Min Act: -0.0001

Data Index: 37445 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3802. Min Act: -0.0001

Data Index: 113455 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.4005. Min Act: -0.0001

Data Index: 887581 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3810. Min Act: -0.0000

Data Index: 854793 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3629. Min Act: -0.0001

Data Index: 421241 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1123560 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3818. Min Act: -0.0001

Data Index: 644863 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3509. Min Act: -0.0001

Data Index: 594699 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3461. Min Act: -0.0001

Data Index: 362158 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1113222 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3598. Min Act: -0.0000

Data Index: 588725 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3167. Min Act: -0.0001

Data Index: 356567 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3476. Min Act: -0.0001

Data Index: 487368 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3208. Min Act: -0.0000

Data Index: 776235 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1329516 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1187810 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3108. Min Act: -0.0000

Data Index: 469522 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3216. Min Act: -0.0001

Data Index: 429446 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.4784. Min Range: -0.4784

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1071586 (C4 (Web Text))

Max Activating Token Index: 13