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

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

Neuron 169 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: 0.3253. Min Range: -0.3253

Max Act: 0.3253. Min Act: -0.0000

Data Index: 181651 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2997. Min Act: -0.0001

Data Index: 123560 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2782. Min Act: -0.0000

Data Index: 912386 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1127116 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2603. Min Act: -0.0000

Data Index: 956127 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2409. Min Act: -0.0001

Data Index: 1014344 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1239663 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1167505 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1008190 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1206334 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2361. Min Act: -0.0000

Data Index: 454616 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2348. Min Act: -0.0000

Data Index: 300885 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2310. Min Act: -0.0001

Data Index: 923229 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1245170 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2327. Min Act: -0.0001

Data Index: 39017 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2052. Min Act: -0.0000

Data Index: 711160 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2128. Min Act: -0.0000

Data Index: 344756 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2091. Min Act: -0.0000

Data Index: 317110 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2137. Min Act: -0.0000

Data Index: 317750 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2136. Min Act: -0.0000

Data Index: 529391 (C4 (Web Text))

Max Activating Token Index: 564