Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 76 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1281312 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1316981 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0563. Min Act: -0.0001

Data Index: 52917 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0559. Min Act: -0.0001

Data Index: 444228 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1103085 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0001

Data Index: 619636 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0487. Min Act: -0.0001

Data Index: 775776 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0506. Min Act: -0.0001

Data Index: 495506 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0452. Min Act: -0.0001

Data Index: 947147 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1417800 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0499. Min Act: -0.0001

Data Index: 185569 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0451. Min Act: -0.0001

Data Index: 868302 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1164785 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1121712 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1297099 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0440. Min Act: -0.0001

Data Index: 487897 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0426. Min Act: -0.0001

Data Index: 968755 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0437. Min Act: -0.0001

Data Index: 893213 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0423. Min Act: -0.0001

Data Index: 325999 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0426. Min Act: -0.0001

Data Index: 995467 (C4 (Web Text))

Max Activating Token Index: 256