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

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

Neuron 1092 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9438. Min Act: 0.0000

Data Index: 197994 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8501. Min Act: -0.0000

Data Index: 148700 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1163794 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8707. Min Act: -0.0000

Data Index: 900324 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9016. Min Act: -0.0000

Data Index: 987903 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7840. Min Act: 0.0000

Data Index: 69914 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7780. Min Act: -0.0000

Data Index: 524141 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7527. Min Act: -0.0000

Data Index: 370917 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7336. Min Act: -0.0000

Data Index: 807475 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7291. Min Act: -0.0000

Data Index: 643193 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6967. Min Act: -0.0000

Data Index: 475403 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6586. Min Act: -0.0000

Data Index: 29823 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1089277 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6840. Min Act: -0.0000

Data Index: 533800 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6732. Min Act: -0.0000

Data Index: 882523 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6648. Min Act: 0.0000

Data Index: 355254 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6821. Min Act: -0.0000

Data Index: 253320 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6631. Min Act: -0.0000

Data Index: 641489 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6613. Min Act: 0.0001

Data Index: 332462 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.6379. Min Act: -0.0000

Data Index: 610242 (C4 (Web Text))

Max Activating Token Index: 625