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

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

Neuron 2462 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7406. Min Range: -3.7406

Max Act: 3.7406. Min Act: -0.0000

Data Index: 537666 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.9367. Min Act: -0.0000

Data Index: 289706 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.7406. Min Range: -3.7406

Max Act: 3.1592. Min Act: -0.0000

Data Index: 105189 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1025589 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.6613. Min Act: -0.0000

Data Index: 529783 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.7917. Min Act: -0.0000

Data Index: 1122015 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.6231. Min Act: -0.0000

Data Index: 604827 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.4616. Min Act: -0.0000

Data Index: 105622 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.3399. Min Act: -0.0000

Data Index: 712673 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.5230. Min Act: -0.0000

Data Index: 415040 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2446. Min Act: -0.0000

Data Index: 61362 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.4445. Min Act: -0.0000

Data Index: 1303199 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1148982 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2982. Min Act: -0.0000

Data Index: 225773 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2661. Min Act: -0.0000

Data Index: 65873 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1127647 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2338. Min Act: -0.0000

Data Index: 1225795 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.2239. Min Act: -0.0000

Data Index: 405030 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.3376. Min Act: -0.0000

Data Index: 313702 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.7406. Min Range: -3.7406

Max Act: 2.0932. Min Act: -0.0000

Data Index: 1110670 (C4 (Web Text))

Max Activating Token Index: 971