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

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

Neuron 1636 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7946. Min Range: -4.7946

Max Act: 4.7946. Min Act: -0.0000

Data Index: 428756 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 4.7946. Min Range: -4.7946

Max Act: 3.8285. Min Act: -0.0000

Data Index: 408528 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 4.7946. Min Range: -4.7946

Max Act: 3.4407. Min Act: -0.0000

Data Index: 292399 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 4.7946. Min Range: -4.7946

Max Act: 3.2462. Min Act: -0.0000

Data Index: 759836 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.9340. Min Act: -0.0000

Data Index: 461190 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.9751. Min Act: -0.0000

Data Index: 328587 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.8338. Min Act: -0.0000

Data Index: 382655 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.7971. Min Act: -0.0000

Data Index: 327592 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.6446. Min Act: -0.0000

Data Index: 1109410 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.7525. Min Act: -0.0000

Data Index: 363156 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.7276. Min Act: -0.0000

Data Index: 679433 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.6142. Min Act: -0.0000

Data Index: 457857 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.5282. Min Act: -0.0000

Data Index: 872620 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.5481. Min Act: -0.0000

Data Index: 384663 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.6189. Min Act: -0.0000

Data Index: 296944 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.5866. Min Act: -0.0000

Data Index: 266282 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.4695. Min Act: -0.0000

Data Index: 509433 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.3198. Min Act: -0.0000

Data Index: 1314017 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.5654. Min Act: -0.0000

Data Index: 1189511 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 4.7946. Min Range: -4.7946

Max Act: 2.4975. Min Act: -0.0000

Data Index: 797376 (C4 (Web Text))

Max Activating Token Index: 281