Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 167 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0004

Data Index: 637833 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0831. Min Act: -0.0004

Data Index: 995566 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0746. Min Act: -0.0004

Data Index: 55838 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0485. Min Act: -0.0004

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0450. Min Act: -0.0004

Data Index: 1140567 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0438. Min Act: -0.0004

Data Index: 1287697 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1523264 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0393. Min Act: -0.0004

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0405. Min Act: -0.0004

Data Index: 92749 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1231517 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0343. Min Act: -0.0004

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1458983 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0337. Min Act: -0.0004

Data Index: 401289 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0326. Min Act: -0.0004

Data Index: 233900 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0296. Min Act: -0.0004

Data Index: 1465384 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0311. Min Act: -0.0004

Data Index: 847047 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1124342 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0295. Min Act: -0.0004

Data Index: 862374 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0291. Min Act: -0.0004

Data Index: 28008 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0280. Min Act: -0.0004

Data Index: 412156 (C4 (Web Text))

Max Activating Token Index: 673