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

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

Neuron 2626 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0206. Min Range: -1.0206

Max Act: 1.0206. Min Act: -0.0002

Data Index: 467140 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9721. Min Act: -0.0002

Data Index: 909558 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9526. Min Act: -0.0002

Data Index: 1215182 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9211. Min Act: -0.0002

Data Index: 1350807 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9217. Min Act: -0.0002

Data Index: 436408 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9056. Min Act: -0.0002

Data Index: 208850 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.9032. Min Act: -0.0002

Data Index: 770721 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8866. Min Act: -0.0002

Data Index: 303539 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8849. Min Act: -0.0002

Data Index: 289901 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8679. Min Act: -0.0002

Data Index: 209179 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8543. Min Act: -0.0002

Data Index: 154403 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8648. Min Act: -0.0002

Data Index: 433717 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8696. Min Act: -0.0002

Data Index: 769130 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8453. Min Act: -0.0002

Data Index: 623320 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8194. Min Act: -0.0002

Data Index: 611830 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8267. Min Act: -0.0002

Data Index: 470882 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8325. Min Act: -0.0002

Data Index: 760600 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8215. Min Act: -0.0002

Data Index: 1201183 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8148. Min Act: -0.0002

Data Index: 73694 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.0206. Min Range: -1.0206

Max Act: 0.8202. Min Act: -0.0002

Data Index: 234022 (C4 (Web Text))

Max Activating Token Index: 977