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

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

Neuron 4680 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: 0.6213. Min Range: -0.6213

Max Act: 0.5999. Min Act: -0.0000

Data Index: 457782 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.6035. Min Act: -0.0000

Data Index: 974525 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.6213. Min Act: -0.0000

Data Index: 819426 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5862. Min Act: -0.0000

Data Index: 441802 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1062966 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5672. Min Act: -0.0000

Data Index: 634863 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5559. Min Act: -0.0000

Data Index: 114582 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5775. Min Act: -0.0000

Data Index: 365927 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1185924 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5320. Min Act: -0.0000

Data Index: 708595 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5751. Min Act: -0.0000

Data Index: 79280 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5510. Min Act: -0.0000

Data Index: 185694 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5101. Min Act: -0.0000

Data Index: 74334 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5200. Min Act: -0.0000

Data Index: 250977 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5671. Min Act: -0.0000

Data Index: 964001 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5312. Min Act: -0.0000

Data Index: 284047 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5304. Min Act: -0.0000

Data Index: 486592 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5329. Min Act: -0.0000

Data Index: 603312 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5316. Min Act: -0.0000

Data Index: 931242 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5295. Min Act: -0.0000

Data Index: 246104 (C4 (Web Text))

Max Activating Token Index: 35