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

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

Neuron 1245 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0430. Min Act: -0.0002

Data Index: 257714 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0438. Min Act: -0.0001

Data Index: 330743 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1148591 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0002

Data Index: 519217 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0388. Min Act: -0.0001

Data Index: 432455 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0407. Min Act: -0.0001

Data Index: 117058 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0385. Min Act: -0.0001

Data Index: 524400 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0380. Min Act: -0.0001

Data Index: 1184799 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1543125 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0391. Min Act: -0.0002

Data Index: 841705 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1432070 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0385. Min Act: -0.0001

Data Index: 149225 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0403. Min Act: -0.0001

Data Index: 502689 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1156346 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1521705 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0378. Min Act: -0.0001

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0387. Min Act: -0.0001

Data Index: 610875 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0364. Min Act: -0.0002

Data Index: 149219 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0355. Min Act: -0.0001

Data Index: 220406 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0368. Min Act: -0.0001

Data Index: 148598 (C4 (Web Text))

Max Activating Token Index: 162