Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0298. Min Act: -0.0006

Data Index: 485278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0276. Min Act: -0.0006

Data Index: 796181 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1630677 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1203188 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1019144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0294. Min Act: -0.0006

Data Index: 472870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1290545 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0297. Min Act: -0.0006

Data Index: 193668 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0291. Min Act: -0.0006

Data Index: 790058 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0300. Min Act: -0.0006

Data Index: 679861 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0276. Min Act: -0.0006

Data Index: 636 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0292. Min Act: -0.0006

Data Index: 701526 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0280. Min Act: -0.0006

Data Index: 399997 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1361674 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0295. Min Act: -0.0006

Data Index: 579129 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0296. Min Act: -0.0006

Data Index: 640234 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0283. Min Act: -0.0006

Data Index: 106556 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0282. Min Act: -0.0006

Data Index: 338386 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0275. Min Act: -0.0006

Data Index: 533242 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0280. Min Act: -0.0006

Data Index: 404660 (C4 (Web Text))

Max Activating Token Index: 502