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

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

Neuron 1466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5161. Min Act: -0.0000

Data Index: 296483 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5299. Min Act: -0.0000

Data Index: 334252 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3480. Min Act: -0.0000

Data Index: 756314 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1265436 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.3098. Min Act: -0.0000

Data Index: 665266 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2986. Min Act: -0.0000

Data Index: 577767 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1354417 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2570. Min Act: -0.0000

Data Index: 421165 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2598. Min Act: -0.0000

Data Index: 701593 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1310469 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1225730 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2583. Min Act: -0.0000

Data Index: 733655 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2557. Min Act: -0.0000

Data Index: 174857 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1213465 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1021429 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1101156 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2278. Min Act: -0.0000

Data Index: 872407 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2339. Min Act: -0.0000

Data Index: 450926 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1343942 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.2246. Min Act: -0.0000

Data Index: 158619 (C4 (Web Text))

Max Activating Token Index: 234