Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8818. Min Act: -0.0000

Data Index: 126582 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.8498. Min Act: -0.0000

Data Index: 67018 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1260236 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1237886 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1648185 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1672. Min Act: -0.0000

Data Index: 754799 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.2221. Min Act: -0.0000

Data Index: 663586 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1696. Min Act: -0.0000

Data Index: 182534 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1310756 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1135360 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1130. Min Act: -0.0000

Data Index: 816113 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1808. Min Act: -0.0000

Data Index: 787170 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1273. Min Act: -0.0000

Data Index: 747538 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1306. Min Act: -0.0000

Data Index: 229336 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0682. Min Act: -0.0000

Data Index: 133685 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.1326. Min Act: -0.0000

Data Index: 69567 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0702. Min Act: -0.0000

Data Index: 878540 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0237. Min Act: -0.0000

Data Index: 238130 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1338149 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 1.8818. Min Range: -1.8818

Max Act: 1.0220. Min Act: -0.0000

Data Index: 537931 (C4 (Web Text))

Max Activating Token Index: 580