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

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

Neuron 345 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: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0004

Data Index: 279283 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0330. Min Act: -0.0004

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0335. Min Act: -0.0004

Data Index: 573344 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0311. Min Act: -0.0004

Data Index: 409634 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0318. Min Act: -0.0004

Data Index: 528210 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1141674 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0311. Min Act: -0.0004

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0300. Min Act: -0.0004

Data Index: 793710 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0263. Min Act: -0.0004

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0266. Min Act: -0.0004

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1019009 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0283. Min Act: -0.0004

Data Index: 473014 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0278. Min Act: -0.0004

Data Index: 227994 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0290. Min Act: -0.0004

Data Index: 194609 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0237. Min Act: -0.0004

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1169831 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0283. Min Act: -0.0004

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0292. Min Act: -0.0004

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0267. Min Act: -0.0004

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 689