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

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

Neuron 4004 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2475. Min Range: -1.2475

Max Act: 1.2475. Min Act: -0.0001

Data Index: 593966 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 1.2475. Min Range: -1.2475

Max Act: 1.0596. Min Act: -0.0001

Data Index: 775755 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 1.2475. Min Range: -1.2475

Max Act: 1.0215. Min Act: -0.0001

Data Index: 830943 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.2475. Min Range: -1.2475

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1071176 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.2475. Min Range: -1.2475

Max Act: 1.0145. Min Act: -0.0001

Data Index: 1056233 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.9782. Min Act: -0.0001

Data Index: 207103 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.9296. Min Act: -0.0001

Data Index: 319000 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.9408. Min Act: -0.0001

Data Index: 176612 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8874. Min Act: -0.0001

Data Index: 249944 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1226438 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.7913. Min Act: -0.0001

Data Index: 606615 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1041596 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.7712. Min Act: -0.0001

Data Index: 889739 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8395. Min Act: -0.0001

Data Index: 297140 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1216882 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8217. Min Act: -0.0001

Data Index: 768245 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.7463. Min Act: -0.0001

Data Index: 475294 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8438. Min Act: -0.0001

Data Index: 686561 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.8256. Min Act: -0.0001

Data Index: 692109 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.2475. Min Range: -1.2475

Max Act: 0.7710. Min Act: -0.0001

Data Index: 513789 (C4 (Web Text))

Max Activating Token Index: 378