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

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

Neuron 4796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.6138. Min Act: -0.0000

Data Index: 326901 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.2639. Min Act: -0.0000

Data Index: 872927 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.6232. Min Act: -0.0000

Data Index: 1350941 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.7157. Min Act: -0.0000

Data Index: 682504 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.1450. Min Act: -0.0000

Data Index: 785103 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.1845. Min Act: -0.0000

Data Index: 178744 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.9717. Min Act: -0.0000

Data Index: 937983 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.6420. Min Act: -0.0000

Data Index: 171638 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.2546. Min Act: -0.0000

Data Index: 1450036 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 4.7157. Min Range: -4.7157

Max Act: 4.0261. Min Act: -0.0000

Data Index: 1214109 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.7434. Min Act: -0.0000

Data Index: 727199 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.6019. Min Act: -0.0000

Data Index: 1053925 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.3910. Min Act: -0.0000

Data Index: 1420712 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.4201. Min Act: -0.0000

Data Index: 107339 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.5348. Min Act: -0.0000

Data Index: 1234269 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.5471. Min Act: -0.0000

Data Index: 506381 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.0854. Min Act: -0.0000

Data Index: 110440 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.2326. Min Act: -0.0000

Data Index: 1003666 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.1596. Min Act: -0.0000

Data Index: 521430 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 4.7157. Min Range: -4.7157

Max Act: 3.0193. Min Act: -0.0000

Data Index: 257705 (C4 (Web Text))

Max Activating Token Index: 163