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

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

Neuron 591 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: 0.5297. Min Range: -0.5297

Max Act: 0.5044. Min Act: -0.0000

Data Index: 489845 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5297. Min Act: -0.0000

Data Index: 562664 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4900. Min Act: -0.0000

Data Index: 70713 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1142327 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5088. Min Act: -0.0000

Data Index: 107871 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4732. Min Act: -0.0000

Data Index: 63956 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1119673 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1313591 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1088237 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4334. Min Act: -0.0000

Data Index: 484051 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4303. Min Act: -0.0000

Data Index: 429427 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4511. Min Act: -0.0000

Data Index: 646522 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4459. Min Act: -0.0000

Data Index: 79445 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1115119 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4090. Min Act: -0.0000

Data Index: 474182 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4178. Min Act: -0.0000

Data Index: 926405 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4144. Min Act: -0.0000

Data Index: 547402 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1010367 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.3857. Min Act: -0.0000

Data Index: 364343 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.3885. Min Act: -0.0000

Data Index: 204675 (C4 (Web Text))

Max Activating Token Index: 694