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

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

Neuron 5532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2426. Min Range: -2.2426

Max Act: 2.1042. Min Act: -0.0000

Data Index: 1122574 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.9797. Min Act: -0.0000

Data Index: 808587 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8289. Min Act: -0.0000

Data Index: 690718 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8952. Min Act: -0.0000

Data Index: 677768 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8936. Min Act: -0.0000

Data Index: 528203 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 2.2426. Min Range: -2.2426

Max Act: 2.2426. Min Act: -0.0000

Data Index: 584767 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8782. Min Act: -0.0000

Data Index: 1077619 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8641. Min Act: -0.0000

Data Index: 613565 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7691. Min Act: -0.0000

Data Index: 69489 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8412. Min Act: -0.0000

Data Index: 466075 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7496. Min Act: -0.0000

Data Index: 514986 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1259801 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1277418 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8194. Min Act: -0.0000

Data Index: 841317 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7960. Min Act: -0.0000

Data Index: 667413 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8070. Min Act: -0.0000

Data Index: 931203 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7882. Min Act: -0.0000

Data Index: 147970 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.9041. Min Act: -0.0000

Data Index: 1246372 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1134555 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7828. Min Act: -0.0000

Data Index: 18155 (C4 (Web Text))

Max Activating Token Index: 4