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

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

Neuron 2967 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 131259 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0461. Min Act: -0.0002

Data Index: 179379 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1386069 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0451. Min Act: -0.0002

Data Index: 683767 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1494688 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1236916 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1097155 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1397607 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0446. Min Act: -0.0002

Data Index: 464612 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1118504 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0444. Min Act: -0.0002

Data Index: 14075 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0436. Min Act: -0.0002

Data Index: 234213 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1647808 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1291984 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0430. Min Act: -0.0002

Data Index: 395097 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0429. Min Act: -0.0002

Data Index: 667634 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0426. Min Act: -0.0002

Data Index: 44051 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0425. Min Act: -0.0002

Data Index: 873956 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1220003 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1330421 (C4 (Web Text))

Max Activating Token Index: 832