Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.5190. Min Act: -0.0001

Data Index: 753083 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.5052. Min Act: -0.0001

Data Index: 397653 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1211187 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4591. Min Act: -0.0001

Data Index: 273026 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4616. Min Act: -0.0001

Data Index: 601880 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4554. Min Act: -0.0001

Data Index: 544487 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1132546 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4593. Min Act: -0.0001

Data Index: 52740 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4465. Min Act: -0.0001

Data Index: 69237 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4435. Min Act: -0.0001

Data Index: 370557 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4266. Min Act: -0.0001

Data Index: 1010850 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4553. Min Act: -0.0001

Data Index: 681104 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4474. Min Act: -0.0001

Data Index: 249046 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1165874 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4281. Min Act: -0.0001

Data Index: 189571 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4495. Min Act: -0.0001

Data Index: 812697 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1064658 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4179. Min Act: -0.0001

Data Index: 496679 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4508. Min Act: -0.0001

Data Index: 880149 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1354051 (C4 (Web Text))

Max Activating Token Index: 349