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

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

Neuron 747 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.4948. Min Act: -0.0000

Data Index: 966410 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.3277. Min Act: -0.0001

Data Index: 368517 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.0676. Min Act: -0.0001

Data Index: 551591 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.0183. Min Act: -0.0001

Data Index: 695373 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.1190. Min Act: -0.0001

Data Index: 130471 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.9633. Min Act: -0.0001

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.0474. Min Act: -0.0001

Data Index: 404372 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.4948. Min Range: -3.4948

Max Act: 3.0377. Min Act: -0.0001

Data Index: 79671 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.7979. Min Act: -0.0001

Data Index: 591726 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.9223. Min Act: -0.0001

Data Index: 1293661 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.9190. Min Act: -0.0001

Data Index: 1184411 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.8649. Min Act: -0.0001

Data Index: 312754 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.8884. Min Act: -0.0000

Data Index: 596948 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.8709. Min Act: -0.0001

Data Index: 101330 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.7771. Min Act: -0.0001

Data Index: 903969 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.8097. Min Act: -0.0001

Data Index: 931626 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.6543. Min Act: -0.0001

Data Index: 1296276 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.4954. Min Act: -0.0001

Data Index: 1135014 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.9285. Min Act: -0.0001

Data Index: 1276600 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.4948. Min Range: -3.4948

Max Act: 2.9044. Min Act: -0.0001

Data Index: 413987 (C4 (Web Text))

Max Activating Token Index: 437