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

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

Neuron 4295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3481. Min Act: -0.0000

Data Index: 851880 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3084. Min Act: -0.0000

Data Index: 335423 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2646. Min Act: -0.0000

Data Index: 759509 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1029501 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2659. Min Act: -0.0000

Data Index: 438686 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1357781 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2352. Min Act: -0.0000

Data Index: 862278 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2657. Min Act: -0.0000

Data Index: 54522 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1076074 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1228614 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2175. Min Act: -0.0000

Data Index: 580806 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2340. Min Act: -0.0000

Data Index: 817811 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1306102 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2400. Min Act: -0.0000

Data Index: 520419 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2141. Min Act: -0.0000

Data Index: 853312 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1213113 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2275. Min Act: -0.0000

Data Index: 772162 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2120. Min Act: -0.0000

Data Index: 288960 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1073076 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2080. Min Act: -0.0000

Data Index: 143115 (C4 (Web Text))

Max Activating Token Index: 890