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

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

Neuron 1107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.0184. Min Range: -4.0184

Max Act: 4.0184. Min Act: -0.0003

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.7335. Min Act: -0.0002

Data Index: 413059 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.7472. Min Act: -0.0002

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.4008. Min Act: -0.0002

Data Index: 1039126 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.3622. Min Act: -0.0002

Data Index: 692936 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.2762. Min Act: -0.0002

Data Index: 383401 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 4.0184. Min Range: -4.0184

Max Act: 3.1277. Min Act: -0.0002

Data Index: 1068354 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9930. Min Act: -0.0002

Data Index: 757631 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9686. Min Act: -0.0002

Data Index: 885747 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9130. Min Act: -0.0002

Data Index: 41706 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9593. Min Act: -0.0002

Data Index: 823097 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9516. Min Act: -0.0002

Data Index: 1125976 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8917. Min Act: -0.0002

Data Index: 132131 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9737. Min Act: -0.0002

Data Index: 799766 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8542. Min Act: -0.0002

Data Index: 682694 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9613. Min Act: -0.0002

Data Index: 1082660 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8938. Min Act: -0.0002

Data Index: 508556 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8943. Min Act: -0.0002

Data Index: 756808 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.9780. Min Act: -0.0002

Data Index: 774137 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 4.0184. Min Range: -4.0184

Max Act: 2.8344. Min Act: -0.0002

Data Index: 693853 (C4 (Web Text))

Max Activating Token Index: 394