Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3111. Min Act: -0.0000

Data Index: 546679 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3364. Min Act: 0.0000

Data Index: 126551 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1221549 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3268. Min Act: -0.0000

Data Index: 420360 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3018. Min Act: -0.0000

Data Index: 820294 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3166. Min Act: -0.0001

Data Index: 232909 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1195769 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3023. Min Act: 0.0000

Data Index: 584135 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2814. Min Act: 0.0001

Data Index: 347899 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2690. Min Act: -0.0001

Data Index: 138005 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2579. Min Act: 0.0001

Data Index: 638128 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1071268 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2609. Min Act: -0.0000

Data Index: 198021 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2446. Min Act: -0.0001

Data Index: 230343 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2495. Min Act: -0.0000

Data Index: 438156 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2415. Min Act: 0.0000

Data Index: 410145 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2464. Min Act: -0.0000

Data Index: 801720 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2441. Min Act: -0.0000

Data Index: 589472 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2354. Min Act: 0.0001

Data Index: 107513 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2235. Min Act: -0.0000

Data Index: 636334 (C4 (Web Text))

Max Activating Token Index: 656