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

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

Neuron 949 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: 1.0807. Min Range: -1.0807

Max Act: 1.0558. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0807. Min Act: -0.0000

Data Index: 974089 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1202774 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9343. Min Act: -0.0000

Data Index: 649320 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9430. Min Act: -0.0000

Data Index: 476643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9598. Min Act: -0.0000

Data Index: 672875 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9227. Min Act: -0.0000

Data Index: 863315 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8888. Min Act: -0.0000

Data Index: 997537 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1223584 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1054479 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9032. Min Act: -0.0000

Data Index: 814171 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1271856 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8796. Min Act: -0.0000

Data Index: 279913 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8758. Min Act: -0.0000

Data Index: 535778 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8186. Min Act: -0.0000

Data Index: 365093 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8301. Min Act: -0.0000

Data Index: 201664 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8248. Min Act: -0.0000

Data Index: 91792 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1339949 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8688. Min Act: -0.0000

Data Index: 214483 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1041045 (C4 (Web Text))

Max Activating Token Index: 421