Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3755 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2369. Min Range: -2.2369

Max Act: 2.1840. Min Act: -0.0000

Data Index: 271143 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 2.2369. Min Range: -2.2369

Max Act: 2.2369. Min Act: -0.0000

Data Index: 690316 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 2.2369. Min Range: -2.2369

Max Act: 2.0889. Min Act: -0.0000

Data Index: 552638 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.5355. Min Act: -0.0000

Data Index: 776309 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.6134. Min Act: -0.0000

Data Index: 285439 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.6818. Min Act: -0.0000

Data Index: 802835 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1248234 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.4442. Min Act: -0.0000

Data Index: 299923 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1346695 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.4960. Min Act: -0.0000

Data Index: 660239 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.4589. Min Act: -0.0000

Data Index: 635972 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.4627. Min Act: -0.0000

Data Index: 949172 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1183643 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.3486. Min Act: -0.0000

Data Index: 553134 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.5041. Min Act: -0.0000

Data Index: 419447 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.3901. Min Act: -0.0000

Data Index: 464041 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1231176 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.3832. Min Act: -0.0000

Data Index: 444211 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.2735. Min Act: -0.0000

Data Index: 305237 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 2.2369. Min Range: -2.2369

Max Act: 1.3430. Min Act: -0.0000

Data Index: 679772 (C4 (Web Text))

Max Activating Token Index: 760