Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3771 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.3411. Min Act: -0.0002

Data Index: 591507 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2938. Min Act: -0.0002

Data Index: 463506 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2616. Min Act: -0.0002

Data Index: 1204029 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2452. Min Act: -0.0002

Data Index: 230652 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2293. Min Act: -0.0002

Data Index: 1152631 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2161. Min Act: -0.0002

Data Index: 1232109 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1253220 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2104. Min Act: -0.0002

Data Index: 323451 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2140. Min Act: -0.0002

Data Index: 925177 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2098. Min Act: -0.0002

Data Index: 1224389 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2062. Min Act: -0.0002

Data Index: 314441 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2090. Min Act: -0.0002

Data Index: 1095712 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1940. Min Act: -0.0002

Data Index: 915245 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1979. Min Act: -0.0002

Data Index: 1187083 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1982. Min Act: -0.0002

Data Index: 1208855 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1995. Min Act: -0.0002

Data Index: 856683 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1083454 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1814. Min Act: -0.0002

Data Index: 1093477 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1840. Min Act: -0.0003

Data Index: 1252060 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1872. Min Act: -0.0002

Data Index: 759641 (C4 (Web Text))

Max Activating Token Index: 455