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

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

Neuron 3103 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0001

Data Index: 522733 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0001

Data Index: 201447 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1113536 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0316. Min Act: -0.0001

Data Index: 764128 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0306. Min Act: -0.0001

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1149165 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0305. Min Act: -0.0001

Data Index: 169983 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0001

Data Index: 223272 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0301. Min Act: -0.0001

Data Index: 626473 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0291. Min Act: -0.0001

Data Index: 986396 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1084288 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0276. Min Act: -0.0001

Data Index: 344132 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0280. Min Act: -0.0001

Data Index: 954492 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0275. Min Act: -0.0001

Data Index: 632717 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0278. Min Act: -0.0001

Data Index: 725630 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1590093 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1399079 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1065185 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0275. Min Act: -0.0001

Data Index: 369531 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0272. Min Act: -0.0001

Data Index: 339308 (C4 (Web Text))

Max Activating Token Index: 470