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

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

Neuron 2201 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7542. Min Range: -7.7542

Max Act: 7.7542. Min Act: -0.0001

Data Index: 396158 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 7.7542. Min Range: -7.7542

Max Act: 7.6941. Min Act: -0.0000

Data Index: 213490 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 7.7542. Min Range: -7.7542

Max Act: 6.5890. Min Act: -0.0000

Data Index: 597350 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 7.7542. Min Range: -7.7542

Max Act: 6.5117. Min Act: -0.0001

Data Index: 878532 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 7.7542. Min Range: -7.7542

Max Act: 6.2263. Min Act: -0.0001

Data Index: 907025 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.6461. Min Act: -0.0000

Data Index: 318130 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 7.7542. Min Range: -7.7542

Max Act: 5.1528. Min Act: -0.0000

Data Index: 676778 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 7.7542. Min Range: -7.7542

Max Act: 5.4690. Min Act: -0.0000

Data Index: 293830 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.7919. Min Act: -0.0001

Data Index: 650184 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.9322. Min Act: -0.0001

Data Index: 306601 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.9315. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 7.7542. Min Range: -7.7542

Max Act: 5.1056. Min Act: -0.0001

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 7.7542. Min Range: -7.7542

Max Act: 5.1523. Min Act: -0.0000

Data Index: 285255 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 7.7542. Min Range: -7.7542

Max Act: 5.2319. Min Act: -0.0000

Data Index: 1281601 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.5061. Min Act: -0.0001

Data Index: 820879 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.5423. Min Act: -0.0001

Data Index: 140750 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.3595. Min Act: -0.0000

Data Index: 658157 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.4985. Min Act: -0.0000

Data Index: 1216779 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 7.7542. Min Range: -7.7542

Max Act: 3.9047. Min Act: -0.0000

Data Index: 956472 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 7.7542. Min Range: -7.7542

Max Act: 4.3097. Min Act: -0.0001

Data Index: 152905 (C4 (Web Text))

Max Activating Token Index: 521