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

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

Neuron 4625 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.9042. Min Act: -0.0000

Data Index: 253609 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1183665 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6357. Min Act: -0.0000

Data Index: 516466 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6126. Min Act: -0.0000

Data Index: 303875 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5898. Min Act: -0.0000

Data Index: 837122 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5633. Min Act: -0.0000

Data Index: 701637 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5632. Min Act: -0.0000

Data Index: 106545 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5538. Min Act: -0.0000

Data Index: 913793 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1186986 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5370. Min Act: -0.0000

Data Index: 363248 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5132. Min Act: -0.0000

Data Index: 302365 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5123. Min Act: -0.0000

Data Index: 852819 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4961. Min Act: -0.0000

Data Index: 602950 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5079. Min Act: -0.0000

Data Index: 309435 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5020. Min Act: -0.0000

Data Index: 797850 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1082431 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5039. Min Act: -0.0000

Data Index: 151969 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5007. Min Act: -0.0000

Data Index: 285666 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4791. Min Act: -0.0000

Data Index: 439029 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4732. Min Act: -0.0000

Data Index: 981320 (C4 (Web Text))

Max Activating Token Index: 1014