Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2448 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2868. Min Act: -0.0002

Data Index: 841095 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0002

Data Index: 775982 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2657. Min Act: -0.0002

Data Index: 224490 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2505. Min Act: -0.0002

Data Index: 1205734 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2573. Min Act: -0.0002

Data Index: 262015 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2595. Min Act: -0.0002

Data Index: 288560 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2517. Min Act: -0.0002

Data Index: 667278 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2484. Min Act: -0.0002

Data Index: 583971 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2467. Min Act: -0.0002

Data Index: 1309208 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2465. Min Act: -0.0002

Data Index: 870559 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2463. Min Act: -0.0002

Data Index: 1334406 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2537. Min Act: -0.0002

Data Index: 662382 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2434. Min Act: -0.0002

Data Index: 20409 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2425. Min Act: -0.0002

Data Index: 864736 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2513. Min Act: -0.0002

Data Index: 1298316 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2423. Min Act: -0.0002

Data Index: 1267565 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2421. Min Act: -0.0002

Data Index: 488082 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2420. Min Act: -0.0002

Data Index: 221086 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2437. Min Act: -0.0002

Data Index: 19215 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2396. Min Act: -0.0002

Data Index: 536499 (C4 (Web Text))

Max Activating Token Index: 38