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

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

Neuron 4676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.2286. Min Act: -0.0000

Data Index: 925363 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1609. Min Act: -0.0000

Data Index: 157944 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1546. Min Act: -0.0000

Data Index: 11538 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1498. Min Act: -0.0000

Data Index: 546899 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1431. Min Act: -0.0000

Data Index: 292655 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1100890 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1174. Min Act: -0.0000

Data Index: 632761 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1194. Min Act: -0.0000

Data Index: 970211 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1188. Min Act: -0.0000

Data Index: 179306 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1481506 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1067. Min Act: -0.0000

Data Index: 563002 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1334937 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1090. Min Act: -0.0000

Data Index: 182921 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1046. Min Act: -0.0000

Data Index: 799958 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1301274 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1182515 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1648620 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1078. Min Act: -0.0000

Data Index: 297596 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1282367 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2286. Min Range: -0.2286

Max Act: 0.1072. Min Act: -0.0000

Data Index: 214422 (C4 (Web Text))

Max Activating Token Index: 644