Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3930. Min Act: -0.0001

Data Index: 679886 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3648. Min Act: -0.0001

Data Index: 130640 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.3228. Min Act: -0.0001

Data Index: 762726 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2916. Min Act: -0.0001

Data Index: 209561 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2713. Min Act: -0.0001

Data Index: 104213 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2714. Min Act: -0.0001

Data Index: 176492 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2580. Min Act: -0.0000

Data Index: 34323 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2458. Min Act: -0.0001

Data Index: 223791 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1234793 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2602. Min Act: -0.0000

Data Index: 198208 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2363. Min Act: -0.0001

Data Index: 56247 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2463. Min Act: -0.0001

Data Index: 492412 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2606. Min Act: -0.0000

Data Index: 19382 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2525. Min Act: -0.0000

Data Index: 700707 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2350. Min Act: -0.0001

Data Index: 171963 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2297. Min Act: -0.0001

Data Index: 630768 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2381. Min Act: -0.0000

Data Index: 212788 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2166. Min Act: -0.0000

Data Index: 159087 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1179689 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.3930. Min Range: -0.3930

Max Act: 0.2427. Min Act: -0.0001

Data Index: 283940 (C4 (Web Text))

Max Activating Token Index: 547