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

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

Neuron 2688 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: 0.6481. Min Range: -0.6481

Max Act: 0.6481. Min Act: -0.0000

Data Index: 344427 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.6383. Min Act: -0.0000

Data Index: 83922 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.6188. Min Act: -0.0000

Data Index: 556217 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5821. Min Act: -0.0000

Data Index: 827894 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5772. Min Act: -0.0000

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5634. Min Act: -0.0000

Data Index: 178904 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5556. Min Act: -0.0000

Data Index: 925086 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5514. Min Act: -0.0000

Data Index: 76947 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5331. Min Act: -0.0000

Data Index: 677066 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4950. Min Act: -0.0000

Data Index: 253299 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4916. Min Act: -0.0000

Data Index: 145343 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4920. Min Act: -0.0000

Data Index: 80827 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4765. Min Act: -0.0000

Data Index: 467762 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4777. Min Act: -0.0000

Data Index: 938415 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1129901 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4501. Min Act: -0.0000

Data Index: 397938 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1142900 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.6481. Min Range: -0.6481

Max Act: 0.4437. Min Act: -0.0000

Data Index: 903037 (C4 (Web Text))

Max Activating Token Index: 735