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

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

Neuron 3955 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: 0.3386. Min Range: -0.3386

Max Act: 0.3386. Min Act: -0.0000

Data Index: 598363 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2903. Min Act: -0.0001

Data Index: 814758 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1216344 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2657. Min Act: -0.0000

Data Index: 129357 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1330018 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1454545 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2652. Min Act: -0.0001

Data Index: 437158 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2530. Min Act: -0.0001

Data Index: 747038 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2408. Min Act: -0.0000

Data Index: 122358 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1401459 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2480. Min Act: -0.0000

Data Index: 695694 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2493. Min Act: -0.0001

Data Index: 460732 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2405. Min Act: -0.0001

Data Index: 908599 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1127438 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1217974 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1175059 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2314. Min Act: -0.0001

Data Index: 152662 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2357. Min Act: -0.0001

Data Index: 215470 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2359. Min Act: -0.0001

Data Index: 350047 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2215. Min Act: -0.0000

Data Index: 448911 (C4 (Web Text))

Max Activating Token Index: 105