Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4761 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.1288. Min Act: -0.0000

Data Index: 483535 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.2141. Min Act: -0.0000

Data Index: 891702 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.0826. Min Act: -0.0000

Data Index: 849365 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.0244. Min Act: -0.0000

Data Index: 18788 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9247. Min Act: -0.0000

Data Index: 239968 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.0356. Min Act: -0.0000

Data Index: 407238 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.1436. Min Act: -0.0000

Data Index: 611100 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.0044. Min Act: -0.0000

Data Index: 721402 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9702. Min Act: -0.0000

Data Index: 19996 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9726. Min Act: -0.0000

Data Index: 711287 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1105485 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.2141. Min Range: -2.2141

Max Act: 2.0724. Min Act: -0.0000

Data Index: 921258 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9410. Min Act: -0.0000

Data Index: 717106 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.8503. Min Act: -0.0000

Data Index: 160259 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9331. Min Act: -0.0000

Data Index: 879488 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.9243. Min Act: -0.0000

Data Index: 633658 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.8939. Min Act: -0.0000

Data Index: 530450 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.8774. Min Act: -0.0000

Data Index: 837735 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.8502. Min Act: -0.0000

Data Index: 308319 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.2141. Min Range: -2.2141

Max Act: 1.8480. Min Act: -0.0000

Data Index: 924424 (C4 (Web Text))

Max Activating Token Index: 370