Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2106 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.4107. Min Act: -0.0001

Data Index: 554831 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3863. Min Act: -0.0000

Data Index: 314446 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3725. Min Act: 0.0000

Data Index: 550515 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1066449 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3718. Min Act: -0.0000

Data Index: 78452 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3438. Min Act: -0.0001

Data Index: 590417 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1204769 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3339. Min Act: -0.0001

Data Index: 161578 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3241. Min Act: -0.0001

Data Index: 842835 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3101. Min Act: 0.0000

Data Index: 617297 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3081. Min Act: -0.0001

Data Index: 1280433 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1039531 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.3102. Min Act: -0.0000

Data Index: 591518 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2977. Min Act: -0.0001

Data Index: 849600 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2877. Min Act: -0.0001

Data Index: 999990 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2851. Min Act: -0.0000

Data Index: 269424 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2921. Min Act: -0.0001

Data Index: 189014 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2870. Min Act: -0.0000

Data Index: 288982 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1189130 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.4107. Min Range: -0.4107

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1240523 (C4 (Web Text))

Max Activating Token Index: 180