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

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

Neuron 4453 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: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0002

Data Index: 354872 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1355. Min Act: -0.0002

Data Index: 512169 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1328. Min Act: -0.0002

Data Index: 318642 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1229. Min Act: -0.0002

Data Index: 555014 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1206498 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1149. Min Act: -0.0002

Data Index: 969642 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1172. Min Act: -0.0002

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1171. Min Act: -0.0002

Data Index: 377161 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1430439 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1232732 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1461852 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1138. Min Act: -0.0002

Data Index: 514751 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1155. Min Act: -0.0002

Data Index: 207024 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1573267 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1098. Min Act: -0.0002

Data Index: 531687 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1106. Min Act: -0.0002

Data Index: 797300 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1107. Min Act: -0.0002

Data Index: 278192 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1100. Min Act: -0.0002

Data Index: 33690 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1102. Min Act: -0.0002

Data Index: 283166 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1115. Min Act: -0.0002

Data Index: 336998 (C4 (Web Text))

Max Activating Token Index: 758