Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3368 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3309. Min Range: -2.3309

Max Act: 2.3309. Min Act: -0.0000

Data Index: 1374068 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 2.3309. Min Range: -2.3309

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1035669 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.9928. Min Act: -0.0000

Data Index: 310646 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.9831. Min Act: -0.0000

Data Index: 797591 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8592. Min Act: -0.0000

Data Index: 951076 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.9602. Min Act: -0.0000

Data Index: 1323344 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.9469. Min Act: -0.0000

Data Index: 775514 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 2.3309. Min Range: -2.3309

Max Act: 2.0553. Min Act: -0.0000

Data Index: 567918 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 2.3309. Min Range: -2.3309

Max Act: 2.0357. Min Act: -0.0000

Data Index: 303827 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.9319. Min Act: -0.0000

Data Index: 792025 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8868. Min Act: -0.0000

Data Index: 854640 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8648. Min Act: -0.0000

Data Index: 84195 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8457. Min Act: -0.0000

Data Index: 314024 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8305. Min Act: -0.0000

Data Index: 216830 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8248. Min Act: -0.0000

Data Index: 950791 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8432. Min Act: -0.0000

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.8304. Min Act: -0.0000

Data Index: 977939 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.5898. Min Act: -0.0000

Data Index: 738028 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.7959. Min Act: -0.0000

Data Index: 659407 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 2.3309. Min Range: -2.3309

Max Act: 1.7021. Min Act: -0.0000

Data Index: 237463 (C4 (Web Text))

Max Activating Token Index: 566