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

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

Neuron 2428 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: 0.5264. Min Range: -0.5264

Max Act: 0.5238. Min Act: -0.0000

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.5264. Min Act: -0.0000

Data Index: 148432 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.4393. Min Act: -0.0000

Data Index: 201358 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.4095. Min Act: -0.0000

Data Index: 63741 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1072603 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1192574 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1045802 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1098203 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3503. Min Act: -0.0000

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1278978 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3226. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1165242 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3284. Min Act: -0.0000

Data Index: 296103 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3372. Min Act: -0.0000

Data Index: 541225 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1322037 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3471. Min Act: -0.0000

Data Index: 659317 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3576. Min Act: -0.0000

Data Index: 491713 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3109. Min Act: -0.0000

Data Index: 364425 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3301. Min Act: -0.0000

Data Index: 457532 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.5264. Min Range: -0.5264

Max Act: 0.3171. Min Act: -0.0000

Data Index: 623591 (C4 (Web Text))

Max Activating Token Index: 274