Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 139 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0005

Data Index: 1068446 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0432. Min Act: -0.0005

Data Index: 149568 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0407. Min Act: -0.0005

Data Index: 214734 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0394. Min Act: -0.0005

Data Index: 36138 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0399. Min Act: -0.0005

Data Index: 267892 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1351746 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0376. Min Act: -0.0005

Data Index: 237581 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1257383 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0348. Min Act: -0.0005

Data Index: 680131 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0342. Min Act: -0.0005

Data Index: 421850 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1089798 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0309. Min Act: -0.0005

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0321. Min Act: -0.0005

Data Index: 384764 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0322. Min Act: -0.0005

Data Index: 10391 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0316. Min Act: -0.0005

Data Index: 846063 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0329. Min Act: -0.0005

Data Index: 1236136 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0335. Min Act: -0.0005

Data Index: 522781 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1290458 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1000576 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0332. Min Act: -0.0005

Data Index: 763534 (C4 (Web Text))

Max Activating Token Index: 583