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

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

Neuron 1269 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.4646. Min Act: -0.0001

Data Index: 135577 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.3580. Min Act: -0.0000

Data Index: 785890 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1285288 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2965. Min Act: -0.0000

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.3073. Min Act: -0.0001

Data Index: 32070 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2832. Min Act: -0.0001

Data Index: 915790 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2873. Min Act: -0.0000

Data Index: 239022 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2635. Min Act: -0.0001

Data Index: 853996 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2720. Min Act: -0.0001

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2498. Min Act: -0.0000

Data Index: 564429 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2415. Min Act: -0.0000

Data Index: 456994 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2361. Min Act: -0.0000

Data Index: 67499 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1507560 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2349. Min Act: -0.0000

Data Index: 428565 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2368. Min Act: -0.0000

Data Index: 952809 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2270. Min Act: -0.0000

Data Index: 343338 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.4646. Min Range: -0.4646

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1029682 (C4 (Web Text))

Max Activating Token Index: 963