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

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

Neuron 3985 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: 0.2713. Min Range: -0.2713

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1072850 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2612. Min Act: -0.0000

Data Index: 369960 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1317457 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1299429 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2520. Min Act: -0.0000

Data Index: 400273 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1117279 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2395. Min Act: -0.0000

Data Index: 900457 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2376. Min Act: -0.0000

Data Index: 424337 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1255105 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1357340 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2210. Min Act: -0.0000

Data Index: 847424 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2117. Min Act: -0.0000

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2125. Min Act: -0.0000

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2158. Min Act: -0.0000

Data Index: 983472 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2228. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2212. Min Act: -0.0000

Data Index: 451571 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2133. Min Act: -0.0000

Data Index: 616612 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2052. Min Act: -0.0000

Data Index: 338818 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2038. Min Act: -0.0000

Data Index: 413540 (C4 (Web Text))

Max Activating Token Index: 186