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

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

Neuron 1815 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: 2.6953. Min Range: -2.6953

Max Act: 2.6953. Min Act: 0.0000

Data Index: 602945 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 2.6953. Min Range: -2.6953

Max Act: 2.3475. Min Act: 0.0001

Data Index: 491207 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 2.6953. Min Range: -2.6953

Max Act: 2.2273. Min Act: -0.0000

Data Index: 842359 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.6953. Min Range: -2.6953

Max Act: 2.0037. Min Act: 0.0000

Data Index: 532816 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8706. Min Act: 0.0000

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1026073 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8986. Min Act: -0.0000

Data Index: 255523 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 2.6953. Min Range: -2.6953

Max Act: 2.0085. Min Act: -0.0000

Data Index: 1124702 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8817. Min Act: -0.0000

Data Index: 1031489 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.7251. Min Act: -0.0000

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8574. Min Act: 0.0000

Data Index: 1237485 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8199. Min Act: -0.0000

Data Index: 191928 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8163. Min Act: 0.0001

Data Index: 973867 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.7035. Min Act: 0.0000

Data Index: 753126 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.8028. Min Act: -0.0000

Data Index: 701161 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1140206 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.6715. Min Act: 0.0001

Data Index: 97250 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.7682. Min Act: 0.0001

Data Index: 1124308 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.7479. Min Act: -0.0000

Data Index: 626122 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.6953. Min Range: -2.6953

Max Act: 1.6323. Min Act: 0.0001

Data Index: 1202253 (C4 (Web Text))

Max Activating Token Index: 170