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

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

Neuron 5111 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: 1.1160. Min Range: -1.1160

Max Act: 1.1119. Min Act: -0.0002

Data Index: 219114 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1125. Min Act: -0.0002

Data Index: 1134128 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0002

Data Index: 588708 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0929. Min Act: -0.0002

Data Index: 1098926 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0837. Min Act: -0.0002

Data Index: 1108315 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0477. Min Act: -0.0002

Data Index: 931639 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0414. Min Act: -0.0002

Data Index: 598886 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0653. Min Act: -0.0003

Data Index: 788387 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0616. Min Act: -0.0002

Data Index: 706528 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0266. Min Act: -0.0002

Data Index: 1103010 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0540. Min Act: -0.0002

Data Index: 492968 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0289. Min Act: -0.0002

Data Index: 66258 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0168. Min Act: -0.0002

Data Index: 147219 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0267. Min Act: -0.0002

Data Index: 720981 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0234. Min Act: -0.0002

Data Index: 449795 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0433. Min Act: -0.0002

Data Index: 101969 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0447. Min Act: -0.0002

Data Index: 484354 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0365. Min Act: -0.0002

Data Index: 715746 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0252. Min Act: -0.0002

Data Index: 443126 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0120. Min Act: -0.0002

Data Index: 975111 (C4 (Web Text))

Max Activating Token Index: 1004