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

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

Neuron 2710 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: 0.3137. Min Range: -0.3137

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1011912 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1209231 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2733. Min Act: -0.0000

Data Index: 457821 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2640. Min Act: 0.0000

Data Index: 638503 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2413. Min Act: -0.0000

Data Index: 600608 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1218033 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2463. Min Act: 0.0000

Data Index: 781920 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2365. Min Act: -0.0000

Data Index: 300284 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1279248 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2286. Min Act: -0.0000

Data Index: 646418 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2351. Min Act: 0.0000

Data Index: 1237945 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2261. Min Act: 0.0000

Data Index: 238924 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2266. Min Act: -0.0000

Data Index: 492986 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2316. Min Act: -0.0000

Data Index: 192571 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2268. Min Act: -0.0000

Data Index: 697836 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2178. Min Act: -0.0000

Data Index: 959437 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2029. Min Act: -0.0000

Data Index: 638395 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1021363 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1090651 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2155. Min Act: -0.0000

Data Index: 139976 (C4 (Web Text))

Max Activating Token Index: 194