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

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

Neuron 86 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.7774. Min Act: -0.0000

Data Index: 1330400 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.6334. Min Act: -0.0000

Data Index: 799201 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.2689. Min Act: -0.0000

Data Index: 1168806 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.2452. Min Act: -0.0000

Data Index: 349315 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.3326. Min Act: -0.0000

Data Index: 1094013 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.6148. Min Act: -0.0000

Data Index: 367657 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.3251. Min Act: -0.0000

Data Index: 235608 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.0136. Min Act: -0.0000

Data Index: 163558 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.1798. Min Act: -0.0000

Data Index: 602938 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.0450. Min Act: -0.0000

Data Index: 533303 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.9241. Min Act: -0.0000

Data Index: 905573 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.1539. Min Act: -0.0000

Data Index: 765262 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.9688. Min Act: -0.0000

Data Index: 226235 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.1195. Min Act: -0.0000

Data Index: 1344576 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.6330. Min Act: -0.0000

Data Index: 8944 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.0591. Min Act: -0.0000

Data Index: 314774 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.7774. Min Range: -3.7774

Max Act: 3.0294. Min Act: -0.0000

Data Index: 419128 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.8289. Min Act: -0.0000

Data Index: 1108164 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.9344. Min Act: -0.0000

Data Index: 450115 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.7774. Min Range: -3.7774

Max Act: 2.7774. Min Act: -0.0000

Data Index: 692033 (C4 (Web Text))

Max Activating Token Index: 201