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

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

Neuron 2745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.8218. Min Act: -0.0000

Data Index: 799232 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.7784. Min Act: -0.0000

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.6694. Min Act: -0.0000

Data Index: 324151 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.5035. Min Act: -0.0000

Data Index: 1004639 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.4305. Min Act: -0.0000

Data Index: 717085 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.4407. Min Act: -0.0000

Data Index: 1180407 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.4163. Min Act: -0.0000

Data Index: 662824 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.3727. Min Act: -0.0000

Data Index: 418447 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.2853. Min Act: -0.0000

Data Index: 266309 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.2858. Min Act: -0.0000

Data Index: 212376 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.2031. Min Act: -0.0000

Data Index: 761688 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1111618 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.1519. Min Act: -0.0000

Data Index: 1460461 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.1861. Min Act: -0.0000

Data Index: 1478193 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.1711. Min Act: -0.0000

Data Index: 131888 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.2324. Min Act: -0.0000

Data Index: 1027272 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.1545. Min Act: -0.0000

Data Index: 1324234 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1143835 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.0955. Min Act: -0.0000

Data Index: 1101110 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 2.8218. Min Range: -2.8218

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1295802 (C4 (Web Text))

Max Activating Token Index: 372