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

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

Neuron 4007 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: 0.6383. Min Range: -0.6383

Max Act: 0.6383. Min Act: -0.0000

Data Index: 250318 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5521. Min Act: 0.0000

Data Index: 483269 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5220. Min Act: -0.0000

Data Index: 290128 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4601. Min Act: -0.0000

Data Index: 515747 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4647. Min Act: 0.0000

Data Index: 993798 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1098804 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4219. Min Act: -0.0000

Data Index: 367279 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4140. Min Act: -0.0000

Data Index: 768760 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3879. Min Act: -0.0000

Data Index: 183260 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4088. Min Act: -0.0000

Data Index: 470475 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3890. Min Act: -0.0000

Data Index: 280314 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4134. Min Act: -0.0000

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4040. Min Act: -0.0000

Data Index: 686111 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3653. Min Act: -0.0000

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3883. Min Act: 0.0000

Data Index: 372720 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4133. Min Act: 0.0000

Data Index: 675987 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3854. Min Act: 0.0000

Data Index: 431114 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3983. Min Act: -0.0000

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3980. Min Act: -0.0000

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.3813. Min Act: -0.0000

Data Index: 144770 (C4 (Web Text))

Max Activating Token Index: 554