Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 768 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 205319 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0434. Min Act: -0.0003

Data Index: 693324 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1100144 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0405. Min Act: -0.0004

Data Index: 650095 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1066944 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0404. Min Act: -0.0003

Data Index: 320765 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0409. Min Act: -0.0003

Data Index: 809256 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0391. Min Act: -0.0003

Data Index: 588375 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0388. Min Act: -0.0004

Data Index: 32470 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0387. Min Act: -0.0003

Data Index: 861480 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0384. Min Act: -0.0003

Data Index: 636745 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1288091 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1170000 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1036985 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1275859 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0359. Min Act: -0.0004

Data Index: 667844 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0350. Min Act: -0.0003

Data Index: 789957 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0347. Min Act: -0.0003

Data Index: 266921 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0343. Min Act: -0.0004

Data Index: 110990 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1320307 (C4 (Web Text))

Max Activating Token Index: 1023