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

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

Neuron 2711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.3032. Min Act: -0.0000

Data Index: 863604 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2385. Min Act: -0.0000

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2477. Min Act: -0.0000

Data Index: 439133 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2692. Min Act: -0.0000

Data Index: 359794 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2560. Min Act: -0.0000

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2456. Min Act: -0.0000

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2314. Min Act: -0.0000

Data Index: 963526 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2385. Min Act: -0.0000

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2467. Min Act: -0.0000

Data Index: 2695 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2316. Min Act: -0.0000

Data Index: 817074 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2436. Min Act: -0.0001

Data Index: 846050 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2273. Min Act: -0.0000

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2393. Min Act: -0.0000

Data Index: 6816 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1572492 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2384. Min Act: -0.0000

Data Index: 447382 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1288581 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2432. Min Act: -0.0000

Data Index: 926740 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1038037 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2367. Min Act: -0.0000

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 982