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

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

Neuron 2013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2967. Min Act: -0.0000

Data Index: 199727 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2725. Min Act: -0.0000

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2735. Min Act: -0.0000

Data Index: 696553 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2676. Min Act: -0.0000

Data Index: 361884 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2581. Min Act: -0.0000

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2489. Min Act: -0.0000

Data Index: 231864 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2531. Min Act: -0.0000

Data Index: 215525 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2475. Min Act: -0.0000

Data Index: 665877 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1293020 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2321. Min Act: -0.0000

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2242. Min Act: -0.0000

Data Index: 66262 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2233. Min Act: -0.0000

Data Index: 786486 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1003152 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1192193 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2114. Min Act: -0.0000

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2177. Min Act: -0.0000

Data Index: 113651 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1277706 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2093. Min Act: -0.0000

Data Index: 378693 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.2967. Min Range: -0.2967

Max Act: 0.2020. Min Act: -0.0000

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 648