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

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

Neuron 805 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.4414. Min Act: -0.0000

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1308835 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1113177 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.4442. Min Act: -0.0000

Data Index: 229474 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3499. Min Act: -0.0000

Data Index: 461020 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3594. Min Act: -0.0000

Data Index: 152650 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3341. Min Act: -0.0000

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3435. Min Act: -0.0000

Data Index: 671028 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3068. Min Act: -0.0000

Data Index: 723335 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3003. Min Act: -0.0000

Data Index: 816090 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1227955 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3013. Min Act: -0.0000

Data Index: 871477 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2870. Min Act: -0.0000

Data Index: 726717 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2942. Min Act: -0.0000

Data Index: 422496 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1108126 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2897. Min Act: -0.0000

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2596. Min Act: -0.0000

Data Index: 550902 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2791. Min Act: -0.0000

Data Index: 276366 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.4625. Min Range: -0.4625

Max Act: 0.2643. Min Act: -0.0000

Data Index: 810492 (C4 (Web Text))

Max Activating Token Index: 763