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

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

Neuron 4209 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8461. Min Act: -0.0000

Data Index: 13492 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7737. Min Act: -0.0000

Data Index: 802387 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5826. Min Act: -0.0000

Data Index: 155892 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1540320 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1504653 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1068153 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5725. Min Act: -0.0000

Data Index: 11888 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1414223 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1475133 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1208789 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.4897. Min Act: -0.0000

Data Index: 293598 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5629. Min Act: -0.0000

Data Index: 921572 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1067308 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.4935. Min Act: -0.0000

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.4987. Min Act: -0.0000

Data Index: 926839 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5410. Min Act: -0.0000

Data Index: 235677 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1566085 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.4501. Min Act: -0.0000

Data Index: 512250 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5163. Min Act: -0.0000

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1014074 (C4 (Web Text))

Max Activating Token Index: 732