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

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

Neuron 3832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.3670. Min Act: -0.0000

Data Index: 962826 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.3927. Min Act: -0.0000

Data Index: 370614 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.2902. Min Act: -0.0000

Data Index: 1052432 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.2599. Min Act: -0.0000

Data Index: 486088 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1085389 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.1757. Min Act: -0.0000

Data Index: 899462 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 2.3927. Min Range: -2.3927

Max Act: 2.0398. Min Act: -0.0000

Data Index: 335204 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8530. Min Act: -0.0000

Data Index: 685622 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.9447. Min Act: -0.0000

Data Index: 527957 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.9440. Min Act: -0.0000

Data Index: 70357 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.9283. Min Act: -0.0000

Data Index: 308998 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8659. Min Act: -0.0000

Data Index: 336798 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8700. Min Act: -0.0000

Data Index: 1168654 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8378. Min Act: -0.0000

Data Index: 20375 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8370. Min Act: -0.0000

Data Index: 405614 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.9311. Min Act: -0.0000

Data Index: 192752 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.8646. Min Act: -0.0000

Data Index: 270127 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.7340. Min Act: -0.0000

Data Index: 791211 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.7231. Min Act: -0.0000

Data Index: 51524 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.3927. Min Range: -2.3927

Max Act: 1.7990. Min Act: -0.0000

Data Index: 997415 (C4 (Web Text))

Max Activating Token Index: 1004