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

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

Neuron 5630 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.5650. Min Act: -0.0000

Data Index: 947217 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.5052. Min Act: -0.0000

Data Index: 168045 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4930. Min Act: -0.0000

Data Index: 146599 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4512. Min Act: 0.0000

Data Index: 658686 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1197323 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4485. Min Act: -0.0000

Data Index: 132258 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1261810 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4182. Min Act: -0.0000

Data Index: 724970 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3969. Min Act: -0.0000

Data Index: 905939 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4152. Min Act: -0.0000

Data Index: 360849 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3759. Min Act: -0.0000

Data Index: 381412 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3854. Min Act: -0.0000

Data Index: 762547 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3871. Min Act: -0.0000

Data Index: 411485 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4062. Min Act: -0.0000

Data Index: 325893 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3722. Min Act: 0.0000

Data Index: 138913 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1207976 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1306262 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3794. Min Act: -0.0000

Data Index: 366877 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3631. Min Act: 0.0000

Data Index: 101629 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1268688 (C4 (Web Text))

Max Activating Token Index: 498