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

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

Neuron 5106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.8848. Min Act: -0.0001

Data Index: 346511 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.6901. Min Act: -0.0001

Data Index: 1121995 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.6734. Min Act: -0.0001

Data Index: 551127 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.8315. Min Act: -0.0001

Data Index: 485830 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.7310. Min Act: -0.0001

Data Index: 808060 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.5065. Min Act: -0.0001

Data Index: 180235 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.6494. Min Act: -0.0001

Data Index: 931677 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.5422. Min Act: -0.0001

Data Index: 99748 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.5279. Min Act: -0.0001

Data Index: 774993 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.5018. Min Act: -0.0001

Data Index: 1260720 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.4431. Min Act: -0.0001

Data Index: 925036 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.4879. Min Act: -0.0001

Data Index: 1114114 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.3991. Min Act: -0.0001

Data Index: 680792 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.5209. Min Act: -0.0001

Data Index: 139193 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.4043. Min Act: -0.0001

Data Index: 1070525 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.3792. Min Act: -0.0001

Data Index: 708339 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.4296. Min Act: -0.0001

Data Index: 909500 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.4276. Min Act: -0.0001

Data Index: 578114 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.3843. Min Act: -0.0001

Data Index: 848695 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.8848. Min Range: -1.8848

Max Act: 1.3640. Min Act: -0.0001

Data Index: 1345595 (C4 (Web Text))

Max Activating Token Index: 388