Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0003

Data Index: 752748 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0601. Min Act: -0.0003

Data Index: 69104 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0570. Min Act: -0.0003

Data Index: 300155 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0540. Min Act: -0.0003

Data Index: 922122 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1292066 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0553. Min Act: -0.0003

Data Index: 415532 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0510. Min Act: -0.0003

Data Index: 638257 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0552. Min Act: -0.0003

Data Index: 935283 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0547. Min Act: -0.0003

Data Index: 131894 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0546. Min Act: -0.0003

Data Index: 254908 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0527. Min Act: -0.0003

Data Index: 269435 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0501. Min Act: -0.0003

Data Index: 106940 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0519. Min Act: -0.0003

Data Index: 618533 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0539. Min Act: -0.0003

Data Index: 882170 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0537. Min Act: -0.0003

Data Index: 999871 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0536. Min Act: -0.0003

Data Index: 606749 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0556. Min Act: -0.0003

Data Index: 707328 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0491. Min Act: -0.0003

Data Index: 52693 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0511. Min Act: -0.0003

Data Index: 201023 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0515. Min Act: -0.0003

Data Index: 389951 (C4 (Web Text))

Max Activating Token Index: 235