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

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

Neuron 6030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.7731. Min Act: -0.0000

Data Index: 874544 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.6233. Min Act: -0.0000

Data Index: 693787 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.3380. Min Act: 0.0001

Data Index: 449794 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.5436. Min Act: -0.0000

Data Index: 954845 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2155. Min Act: -0.0000

Data Index: 1313736 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.4767. Min Act: -0.0000

Data Index: 582574 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2922. Min Act: -0.0000

Data Index: 1108544 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.3834. Min Act: -0.0000

Data Index: 35199 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2450. Min Act: -0.0000

Data Index: 164306 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2542. Min Act: -0.0000

Data Index: 93263 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2283. Min Act: -0.0000

Data Index: 665245 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 2.7731. Min Range: -2.7731

Max Act: 1.8422. Min Act: -0.0000

Data Index: 134892 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.1731. Min Act: -0.0000

Data Index: 444531 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.2936. Min Act: -0.0000

Data Index: 649886 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.0150. Min Act: -0.0000

Data Index: 756208 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.1218. Min Act: -0.0000

Data Index: 818273 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1335823 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.1071. Min Act: -0.0000

Data Index: 411320 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 2.7731. Min Range: -2.7731

Max Act: 1.9548. Min Act: -0.0000

Data Index: 98592 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 2.7731. Min Range: -2.7731

Max Act: 2.0106. Min Act: -0.0000

Data Index: 281490 (C4 (Web Text))

Max Activating Token Index: 688