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

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

Neuron 1199 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1562364 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5934. Min Act: -0.0000

Data Index: 782422 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1388736 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5677. Min Act: 0.0000

Data Index: 1386626 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1417213 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1569763 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5094. Min Act: -0.0000

Data Index: 208423 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4950. Min Act: -0.0000

Data Index: 778250 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1122608 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1415725 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4824. Min Act: -0.0000

Data Index: 153765 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4547. Min Act: -0.0000

Data Index: 880522 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1328748 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4837. Min Act: -0.0000

Data Index: 63706 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1496051 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1604856 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1523838 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4663. Min Act: 0.0000

Data Index: 411915 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1395402 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1464953 (Python Code)

Max Activating Token Index: 683