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

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

Neuron 2657 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.8189. Min Act: -0.0000

Data Index: 320488 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.5577. Min Act: -0.0000

Data Index: 453543 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.4999. Min Act: -0.0000

Data Index: 603269 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.2659. Min Act: -0.0000

Data Index: 1243512 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.2512. Min Act: -0.0000

Data Index: 1235720 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.2555. Min Act: -0.0000

Data Index: 123106 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.0688. Min Act: -0.0000

Data Index: 1239259 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.1337. Min Act: -0.0000

Data Index: 330367 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.1021. Min Act: -0.0000

Data Index: 1062658 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.0786. Min Act: -0.0000

Data Index: 600098 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.2458. Min Act: -0.0000

Data Index: 925070 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.9982. Min Act: -0.0000

Data Index: 678574 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 4.8189. Min Range: -4.8189

Max Act: 4.1132. Min Act: -0.0000

Data Index: 714103 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.9240. Min Act: -0.0000

Data Index: 340765 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.8104. Min Act: -0.0000

Data Index: 311381 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.9495. Min Act: -0.0000

Data Index: 11544 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.7257. Min Act: -0.0000

Data Index: 1326975 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.5286. Min Act: -0.0000

Data Index: 599446 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.5102. Min Act: -0.0000

Data Index: 788413 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.8189. Min Range: -4.8189

Max Act: 3.6554. Min Act: -0.0000

Data Index: 725230 (C4 (Web Text))

Max Activating Token Index: 831