Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.3086. Min Act: -0.0000

Data Index: 623723 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1345290 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2750. Min Act: -0.0000

Data Index: 134340 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2570. Min Act: -0.0000

Data Index: 349888 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2705. Min Act: -0.0000

Data Index: 416493 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2575. Min Act: -0.0000

Data Index: 142390 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1197067 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2491. Min Act: -0.0000

Data Index: 577808 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2479. Min Act: -0.0000

Data Index: 493554 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1107266 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2552. Min Act: -0.0000

Data Index: 753798 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1141309 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2504. Min Act: 0.0001

Data Index: 382639 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1299890 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1084910 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2519. Min Act: 0.0000

Data Index: 1231804 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2362. Min Act: -0.0000

Data Index: 378922 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2283. Min Act: -0.0000

Data Index: 928953 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2374. Min Act: -0.0000

Data Index: 831297 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2279. Min Act: -0.0000

Data Index: 106723 (C4 (Web Text))

Max Activating Token Index: 773