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

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

Neuron 3304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1319901 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0000

Data Index: 446165 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0487. Min Act: -0.0000

Data Index: 7369 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0461. Min Act: -0.0000

Data Index: 312300 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1339219 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0465. Min Act: -0.0000

Data Index: 1160967 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0487. Min Act: -0.0000

Data Index: 79508 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1021755 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0443. Min Act: -0.0000

Data Index: 329704 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1065075 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0448. Min Act: -0.0001

Data Index: 777126 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0385. Min Act: -0.0001

Data Index: 681040 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0430. Min Act: -0.0001

Data Index: 659262 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0423. Min Act: -0.0000

Data Index: 460402 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0425. Min Act: -0.0000

Data Index: 401193 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1237373 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0371. Min Act: -0.0000

Data Index: 503234 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0442. Min Act: -0.0000

Data Index: 309011 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1270562 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0397. Min Act: -0.0000

Data Index: 440975 (C4 (Web Text))

Max Activating Token Index: 414