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

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

Neuron 17 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: 0.0236. Min Range: -0.0236

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1532 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0232. Min Act: -0.0006

Data Index: 871800 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0236. Min Act: -0.0006

Data Index: 161960 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0226. Min Act: -0.0006

Data Index: 222489 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0221. Min Act: -0.0006

Data Index: 580487 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0217. Min Act: -0.0006

Data Index: 717600 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0213. Min Act: -0.0006

Data Index: 623700 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0211. Min Act: -0.0006

Data Index: 221737 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0212. Min Act: -0.0006

Data Index: 892330 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1186876 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1020197 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0212. Min Act: -0.0006

Data Index: 20584 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0203. Min Act: -0.0006

Data Index: 957740 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0204. Min Act: -0.0006

Data Index: 393525 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0200. Min Act: -0.0006

Data Index: 833378 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0204. Min Act: -0.0006

Data Index: 654331 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0202. Min Act: -0.0006

Data Index: 556409 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0196. Min Act: -0.0006

Data Index: 336070 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0200. Min Act: -0.0006

Data Index: 540402 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0191. Min Act: -0.0006

Data Index: 163633 (C4 (Web Text))

Max Activating Token Index: 862