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

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

Neuron 2270 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.8520. Min Act: -0.0000

Data Index: 214005 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7635. Min Act: -0.0000

Data Index: 22177 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6787. Min Act: -0.0000

Data Index: 496108 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6907. Min Act: -0.0000

Data Index: 496466 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1117104 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6628. Min Act: -0.0000

Data Index: 658388 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1025036 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1299370 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1099584 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1243992 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5924. Min Act: -0.0000

Data Index: 718119 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1143437 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5456. Min Act: -0.0000

Data Index: 366239 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5631. Min Act: -0.0000

Data Index: 974983 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5545. Min Act: -0.0000

Data Index: 308298 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5663. Min Act: -0.0000

Data Index: 100260 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5578. Min Act: -0.0000

Data Index: 215626 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5038. Min Act: -0.0000

Data Index: 340573 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1069887 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1193762 (C4 (Web Text))

Max Activating Token Index: 882