Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1182888 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1305248 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7141. Min Act: -0.0000

Data Index: 996249 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6975. Min Act: -0.0000

Data Index: 669450 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6653. Min Act: -0.0001

Data Index: 18428 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6609. Min Act: -0.0000

Data Index: 110473 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6786. Min Act: -0.0000

Data Index: 63307 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6818. Min Act: -0.0000

Data Index: 651366 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6781. Min Act: -0.0001

Data Index: 598293 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6069. Min Act: -0.0000

Data Index: 387893 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6400. Min Act: -0.0000

Data Index: 688208 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6220. Min Act: -0.0001

Data Index: 211605 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6138. Min Act: -0.0000

Data Index: 23464 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1240089 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5031. Min Act: -0.0001

Data Index: 18769 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1174067 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5325. Min Act: -0.0001

Data Index: 761155 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1291886 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1113537 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1050777 (C4 (Web Text))

Max Activating Token Index: 584