Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 24 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1108493 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0509. Min Act: -0.0002

Data Index: 629131 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0501. Min Act: -0.0003

Data Index: 937241 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1031259 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1211003 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0485. Min Act: -0.0003

Data Index: 563078 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0478. Min Act: -0.0003

Data Index: 179142 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1467684 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0472. Min Act: -0.0003

Data Index: 754241 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0003

Data Index: 742316 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0461. Min Act: -0.0003

Data Index: 174070 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0469. Min Act: -0.0003

Data Index: 205347 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0463. Min Act: -0.0003

Data Index: 972174 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1282773 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1013714 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0445. Min Act: -0.0004

Data Index: 202991 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0462. Min Act: -0.0003

Data Index: 858533 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0444. Min Act: -0.0003

Data Index: 500239 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1085120 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0452. Min Act: -0.0003

Data Index: 283713 (C4 (Web Text))

Max Activating Token Index: 930