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

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

Neuron 1871 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: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0001

Data Index: 458131 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2667. Min Act: -0.0001

Data Index: 883038 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2625. Min Act: -0.0000

Data Index: 990640 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2557. Min Act: -0.0001

Data Index: 135727 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2570. Min Act: -0.0000

Data Index: 299992 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2590. Min Act: -0.0000

Data Index: 588852 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1219453 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2574. Min Act: -0.0001

Data Index: 457063 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2572. Min Act: -0.0001

Data Index: 483869 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2454. Min Act: -0.0000

Data Index: 65183 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2469. Min Act: -0.0000

Data Index: 183575 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2524. Min Act: -0.0001

Data Index: 787160 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1014275 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2461. Min Act: -0.0000

Data Index: 892618 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2524. Min Act: -0.0001

Data Index: 404084 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2599. Min Act: -0.0000

Data Index: 224648 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2493. Min Act: -0.0001

Data Index: 109805 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2509. Min Act: -0.0000

Data Index: 390550 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1247252 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2475. Min Act: -0.0000

Data Index: 98418 (C4 (Web Text))

Max Activating Token Index: 736