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

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

Neuron 1338 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: 0.5448. Min Range: -0.5448

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1411456 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1256964 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4807. Min Act: -0.0000

Data Index: 517301 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1119704 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4706. Min Act: -0.0000

Data Index: 574130 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4703. Min Act: -0.0000

Data Index: 272010 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4661. Min Act: -0.0000

Data Index: 211104 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1356421 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4811. Min Act: -0.0000

Data Index: 519957 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1378192 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4916. Min Act: -0.0000

Data Index: 916658 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4748. Min Act: -0.0000

Data Index: 828027 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4584. Min Act: -0.0000

Data Index: 678531 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1655700 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4473. Min Act: -0.0000

Data Index: 385976 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4437. Min Act: -0.0000

Data Index: 800213 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4179. Min Act: -0.0000

Data Index: 204091 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4269. Min Act: -0.0000

Data Index: 949825 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.5448. Min Range: -0.5448

Max Act: 0.4136. Min Act: -0.0000

Data Index: 777647 (C4 (Web Text))

Max Activating Token Index: 696