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

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

Neuron 3014 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: 1.0197. Min Range: -1.0197

Max Act: 0.9987. Min Act: -0.0002

Data Index: 770530 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.0197. Min Range: -1.0197

Max Act: 1.0197. Min Act: -0.0002

Data Index: 1034082 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9961. Min Act: -0.0002

Data Index: 124643 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9731. Min Act: -0.0002

Data Index: 359476 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9737. Min Act: -0.0002

Data Index: 1210713 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9598. Min Act: -0.0002

Data Index: 1016709 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9598. Min Act: -0.0002

Data Index: 447951 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9723. Min Act: -0.0002

Data Index: 429397 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9709. Min Act: -0.0002

Data Index: 869746 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9373. Min Act: -0.0002

Data Index: 862921 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9351. Min Act: -0.0002

Data Index: 1095032 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9271. Min Act: -0.0002

Data Index: 698314 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9384. Min Act: -0.0002

Data Index: 353975 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9277. Min Act: -0.0002

Data Index: 1194359 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9352. Min Act: -0.0002

Data Index: 1358444 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9110. Min Act: -0.0002

Data Index: 554865 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9197. Min Act: -0.0002

Data Index: 357005 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9159. Min Act: -0.0002

Data Index: 722319 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9190. Min Act: -0.0002

Data Index: 868638 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.8883. Min Act: -0.0002

Data Index: 768941 (C4 (Web Text))

Max Activating Token Index: 3