Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1901 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0759. Min Act: -0.0001

Data Index: 801025 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.0759. Min Range: -1.0759

Max Act: 1.0219. Min Act: -0.0000

Data Index: 997245 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9101. Min Act: -0.0000

Data Index: 84173 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.9335. Min Act: -0.0001

Data Index: 992156 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8715. Min Act: -0.0000

Data Index: 466799 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8752. Min Act: -0.0001

Data Index: 718284 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8846. Min Act: -0.0001

Data Index: 271515 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8489. Min Act: -0.0001

Data Index: 461834 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8338. Min Act: -0.0001

Data Index: 313797 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8268. Min Act: -0.0001

Data Index: 1036936 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8338. Min Act: -0.0000

Data Index: 9054 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8320. Min Act: -0.0001

Data Index: 812979 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.8149. Min Act: -0.0000

Data Index: 19767 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7784. Min Act: -0.0001

Data Index: 302027 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7618. Min Act: -0.0001

Data Index: 20432 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7840. Min Act: -0.0001

Data Index: 205738 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7524. Min Act: -0.0001

Data Index: 932277 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7673. Min Act: -0.0001

Data Index: 196562 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7438. Min Act: -0.0001

Data Index: 1327506 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.0759. Min Range: -1.0759

Max Act: 0.7179. Min Act: -0.0001

Data Index: 688264 (C4 (Web Text))

Max Activating Token Index: 278