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

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

Neuron 975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1995. Min Range: -3.1995

Max Act: 1.2278. Min Act: -0.0000

Data Index: 285047 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 3.1995. Min Range: -3.1995

Max Act: 3.1995. Min Act: -0.0000

Data Index: 934127 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0918. Min Act: -0.0000

Data Index: 259619 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0518. Min Act: -0.0000

Data Index: 716489 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1066095 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1117386 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0460. Min Act: -0.0000

Data Index: 543095 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0494. Min Act: -0.0000

Data Index: 161482 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0485. Min Act: -0.0000

Data Index: 626751 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0051. Min Act: -0.0000

Data Index: 491901 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0440. Min Act: -0.0000

Data Index: 945003 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0481. Min Act: -0.0000

Data Index: 599924 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1089724 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0456. Min Act: -0.0000

Data Index: 246115 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0458. Min Act: -0.0000

Data Index: 723811 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0626. Min Act: -0.0000

Data Index: 585055 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0435. Min Act: -0.0000

Data Index: 688864 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1375062 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0393. Min Act: -0.0000

Data Index: 167790 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.1995. Min Range: -3.1995

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1502174 (Python Code)

Max Activating Token Index: 1010