Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1050 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0004

Data Index: 792812 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0525. Min Act: -0.0004

Data Index: 466527 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0499. Min Act: -0.0004

Data Index: 751228 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0496. Min Act: -0.0004

Data Index: 1248058 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0504. Min Act: -0.0005

Data Index: 1272743 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0484. Min Act: -0.0005

Data Index: 1182212 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0463. Min Act: -0.0004

Data Index: 336894 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0480. Min Act: -0.0005

Data Index: 921955 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0459. Min Act: -0.0004

Data Index: 1011214 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1330292 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0451. Min Act: -0.0004

Data Index: 829221 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0449. Min Act: -0.0004

Data Index: 917376 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0454. Min Act: -0.0004

Data Index: 298070 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0440. Min Act: -0.0004

Data Index: 153315 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0445. Min Act: -0.0004

Data Index: 494906 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0444. Min Act: -0.0005

Data Index: 881877 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0434. Min Act: -0.0004

Data Index: 1247544 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0443. Min Act: -0.0004

Data Index: 874004 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0432. Min Act: -0.0005

Data Index: 996827 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0440. Min Act: -0.0004

Data Index: 433273 (C4 (Web Text))

Max Activating Token Index: 612