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

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

Neuron 67 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.3084. Min Act: -0.0000

Data Index: 177208 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2828. Min Act: -0.0000

Data Index: 459099 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.3044. Min Act: -0.0000

Data Index: 665085 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2567. Min Act: -0.0000

Data Index: 474135 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2564. Min Act: -0.0000

Data Index: 693963 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2543. Min Act: -0.0000

Data Index: 313199 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1071106 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2603. Min Act: -0.0000

Data Index: 630203 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2463. Min Act: -0.0000

Data Index: 817178 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2437. Min Act: -0.0000

Data Index: 152386 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1203773 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2214. Min Act: -0.0000

Data Index: 890478 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2370. Min Act: -0.0000

Data Index: 333369 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1083649 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2280. Min Act: -0.0000

Data Index: 316383 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2520. Min Act: -0.0000

Data Index: 542743 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1015776 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2313. Min Act: -0.0000

Data Index: 174792 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2229. Min Act: -0.0000

Data Index: 262031 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2130. Min Act: -0.0000

Data Index: 554655 (C4 (Web Text))

Max Activating Token Index: 566