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

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

Neuron 5912 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.9233. Min Act: -0.0000

Data Index: 294071 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.5242. Min Act: -0.0000

Data Index: 767659 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.5071. Min Act: -0.0001

Data Index: 232754 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.5121. Min Act: -0.0001

Data Index: 837454 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.4728. Min Act: -0.0001

Data Index: 445146 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.3198. Min Act: -0.0000

Data Index: 1049020 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.4729. Min Act: -0.0001

Data Index: 438769 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.4247. Min Act: -0.0000

Data Index: 1312754 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.4022. Min Act: -0.0000

Data Index: 167372 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.5004. Min Act: -0.0001

Data Index: 1242179 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2186. Min Act: -0.0000

Data Index: 690010 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2244. Min Act: -0.0000

Data Index: 1121603 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.3357. Min Act: -0.0001

Data Index: 316355 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.3120. Min Act: -0.0000

Data Index: 651259 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2777. Min Act: -0.0000

Data Index: 1105299 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2713. Min Act: -0.0001

Data Index: 468860 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.1707. Min Act: -0.0000

Data Index: 1110204 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2588. Min Act: -0.0001

Data Index: 985114 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1105671 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.9233. Min Range: -2.9233

Max Act: 2.2520. Min Act: -0.0001

Data Index: 1308341 (C4 (Web Text))

Max Activating Token Index: 516