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

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

Neuron 1097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7440. Min Range: -1.7440

Max Act: 1.7440. Min Act: -0.0000

Data Index: 835409 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.7440. Min Range: -1.7440

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1344996 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.7440. Min Range: -1.7440

Max Act: 1.0437. Min Act: -0.0000

Data Index: 917180 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.9771. Min Act: -0.0000

Data Index: 50016 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1068997 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.9610. Min Act: -0.0000

Data Index: 838618 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.9544. Min Act: -0.0000

Data Index: 335661 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8471. Min Act: -0.0000

Data Index: 801849 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8923. Min Act: -0.0000

Data Index: 110128 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8912. Min Act: -0.0000

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1070905 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8087. Min Act: -0.0000

Data Index: 478742 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1027960 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.7491. Min Act: -0.0000

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1058497 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8290. Min Act: -0.0000

Data Index: 434150 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8260. Min Act: -0.0000

Data Index: 147023 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8749. Min Act: -0.0000

Data Index: 636756 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.7440. Min Range: -1.7440

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1151162 (C4 (Web Text))

Max Activating Token Index: 553