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

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

Neuron 3121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1578. Min Range: -2.1578

Max Act: 2.1578. Min Act: -0.0000

Data Index: 950791 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.8143. Min Act: -0.0000

Data Index: 235248 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.7455. Min Act: -0.0000

Data Index: 348846 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3035. Min Act: -0.0000

Data Index: 194193 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.6310. Min Act: -0.0000

Data Index: 413169 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1009933 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.6447. Min Act: -0.0000

Data Index: 327555 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.4183. Min Act: -0.0000

Data Index: 358164 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3102. Min Act: -0.0000

Data Index: 839664 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.4395. Min Act: -0.0000

Data Index: 620445 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3861. Min Act: -0.0000

Data Index: 809307 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.5101. Min Act: -0.0000

Data Index: 650611 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.4664. Min Act: -0.0000

Data Index: 803314 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3369. Min Act: -0.0000

Data Index: 412395 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.4167. Min Act: -0.0000

Data Index: 664325 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1024334 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.3224. Min Act: -0.0000

Data Index: 119841 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1302137 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.2283. Min Act: -0.0000

Data Index: 174700 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.1578. Min Range: -2.1578

Max Act: 1.1784. Min Act: -0.0000

Data Index: 917485 (C4 (Web Text))

Max Activating Token Index: 243