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

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

Neuron 2908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0002

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0535. Min Act: -0.0002

Data Index: 629726 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0494. Min Act: -0.0002

Data Index: 177512 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0501. Min Act: -0.0002

Data Index: 402644 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1307667 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0522. Min Act: -0.0002

Data Index: 249612 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0465. Min Act: -0.0002

Data Index: 202400 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0435. Min Act: -0.0002

Data Index: 978516 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0479. Min Act: -0.0002

Data Index: 677534 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0414. Min Act: -0.0002

Data Index: 365157 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0424. Min Act: -0.0002

Data Index: 875119 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0455. Min Act: -0.0002

Data Index: 508046 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0418. Min Act: -0.0002

Data Index: 237362 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0460. Min Act: -0.0002

Data Index: 598135 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0437. Min Act: -0.0002

Data Index: 749728 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0432. Min Act: -0.0002

Data Index: 112310 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0430. Min Act: -0.0002

Data Index: 307145 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0461. Min Act: -0.0002

Data Index: 453777 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0411. Min Act: -0.0002

Data Index: 659190 (C4 (Web Text))

Max Activating Token Index: 757