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

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

Neuron 535 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0003

Data Index: 238941 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0547. Min Act: -0.0003

Data Index: 872106 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0530. Min Act: -0.0002

Data Index: 158235 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0493. Min Act: -0.0003

Data Index: 925143 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0493. Min Act: -0.0003

Data Index: 810162 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0491. Min Act: -0.0003

Data Index: 524712 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0483. Min Act: -0.0003

Data Index: 35530 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0460. Min Act: -0.0003

Data Index: 19790 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0446. Min Act: -0.0003

Data Index: 866361 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0437. Min Act: -0.0003

Data Index: 44185 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0452. Min Act: -0.0003

Data Index: 653481 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0444. Min Act: -0.0003

Data Index: 704913 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0447. Min Act: -0.0003

Data Index: 28778 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0433. Min Act: -0.0003

Data Index: 574043 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0428. Min Act: -0.0003

Data Index: 773416 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0433. Min Act: -0.0003

Data Index: 255737 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0433. Min Act: -0.0003

Data Index: 326647 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0423. Min Act: -0.0003

Data Index: 364726 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0423. Min Act: -0.0003

Data Index: 80166 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1094707 (C4 (Web Text))

Max Activating Token Index: 285