Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 239 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0006

Data Index: 144242 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0322. Min Act: -0.0005

Data Index: 429640 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0325. Min Act: -0.0006

Data Index: 702248 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0282. Min Act: -0.0006

Data Index: 595238 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1070996 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0263. Min Act: -0.0006

Data Index: 687514 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1182520 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1330940 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0259. Min Act: -0.0006

Data Index: 42298 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0252. Min Act: -0.0006

Data Index: 563119 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0254. Min Act: -0.0006

Data Index: 836353 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0249. Min Act: -0.0006

Data Index: 833532 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0252. Min Act: -0.0006

Data Index: 56601 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0251. Min Act: -0.0006

Data Index: 890920 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1336112 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0243. Min Act: -0.0006

Data Index: 629293 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0248. Min Act: -0.0006

Data Index: 74283 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0246. Min Act: -0.0007

Data Index: 67949 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0246. Min Act: -0.0006

Data Index: 713942 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0245. Min Act: -0.0006

Data Index: 79970 (C4 (Web Text))

Max Activating Token Index: 1006