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

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

Neuron 3342 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: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1310835 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0486. Min Act: -0.0001

Data Index: 719832 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0477. Min Act: -0.0001

Data Index: 715455 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0001

Data Index: 979845 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0358. Min Act: -0.0001

Data Index: 493156 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0409. Min Act: -0.0001

Data Index: 21501 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0389. Min Act: -0.0001

Data Index: 219441 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0380. Min Act: -0.0001

Data Index: 827600 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0395. Min Act: -0.0001

Data Index: 835682 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1059688 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0371. Min Act: -0.0001

Data Index: 892512 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0331. Min Act: -0.0001

Data Index: 182488 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1198 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1148733 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0416. Min Act: -0.0001

Data Index: 500924 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0352. Min Act: -0.0001

Data Index: 590359 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0314. Min Act: -0.0001

Data Index: 604045 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1149216 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0312. Min Act: -0.0001

Data Index: 326425 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0338. Min Act: -0.0001

Data Index: 889321 (C4 (Web Text))

Max Activating Token Index: 89