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

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

Neuron 2392 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1110. Min Range: -2.1110

Max Act: 2.1110. Min Act: -0.0000

Data Index: 78293 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.9139. Min Act: -0.0000

Data Index: 112936 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1083042 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1155502 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4812. Min Act: -0.0000

Data Index: 982453 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4685. Min Act: -0.0000

Data Index: 115897 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.5444. Min Act: -0.0000

Data Index: 924816 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1235834 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.3731. Min Act: -0.0000

Data Index: 869465 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4477. Min Act: -0.0000

Data Index: 552216 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4065. Min Act: -0.0000

Data Index: 149338 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1054151 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1274380 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4807. Min Act: -0.0000

Data Index: 1006826 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2454. Min Act: -0.0000

Data Index: 407563 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2447. Min Act: -0.0000

Data Index: 590789 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2429. Min Act: -0.0000

Data Index: 487362 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1297102 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1269757 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.2189. Min Act: -0.0000

Data Index: 21099 (C4 (Web Text))

Max Activating Token Index: 181