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

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

Neuron 860 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: 0.0548. Min Range: -0.0548

Max Act: 0.0544. Min Act: -0.0004

Data Index: 876036 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0003

Data Index: 286479 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1056274 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0493. Min Act: -0.0003

Data Index: 733861 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0498. Min Act: -0.0004

Data Index: 243057 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0499. Min Act: -0.0004

Data Index: 1229321 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1248513 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0476. Min Act: -0.0004

Data Index: 950721 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1079230 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1025303 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0459. Min Act: -0.0003

Data Index: 624835 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0460. Min Act: -0.0003

Data Index: 101532 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0471. Min Act: -0.0003

Data Index: 176552 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0451. Min Act: -0.0003

Data Index: 386285 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1059215 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0449. Min Act: -0.0003

Data Index: 899956 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0435. Min Act: -0.0003

Data Index: 615080 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1322727 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1048045 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0448. Min Act: -0.0004

Data Index: 205420 (C4 (Web Text))

Max Activating Token Index: 559