Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0000

Data Index: 226402 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1312563 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1107696 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0956. Min Act: -0.0000

Data Index: 273214 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0930. Min Act: -0.0000

Data Index: 126233 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0842. Min Act: -0.0000

Data Index: 913222 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1327307 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0850. Min Act: -0.0000

Data Index: 836367 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0843. Min Act: -0.0000

Data Index: 220816 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0923. Min Act: -0.0000

Data Index: 73126 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0813. Min Act: -0.0000

Data Index: 230000 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0807. Min Act: -0.0000

Data Index: 942934 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0810. Min Act: -0.0000

Data Index: 125120 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0814. Min Act: -0.0000

Data Index: 955810 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0856. Min Act: -0.0000

Data Index: 104861 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1057015 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1214003 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0742. Min Act: -0.0000

Data Index: 661824 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1129028 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0766. Min Act: -0.0000

Data Index: 593753 (C4 (Web Text))

Max Activating Token Index: 244