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

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

Neuron 1670 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: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0000

Data Index: 57395 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1343. Min Act: -0.0000

Data Index: 195795 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1337. Min Act: -0.0000

Data Index: 687185 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1617914 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1137. Min Act: -0.0000

Data Index: 988416 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1070. Min Act: -0.0000

Data Index: 158419 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1235686 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0918. Min Act: -0.0000

Data Index: 964624 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1223100 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0932. Min Act: -0.0000

Data Index: 759257 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0880. Min Act: -0.0000

Data Index: 888457 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1043. Min Act: -0.0000

Data Index: 434511 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1327438 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1514088 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0800. Min Act: -0.0000

Data Index: 953074 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0801. Min Act: -0.0000

Data Index: 167902 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1454529 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1429579 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0683. Min Act: -0.0000

Data Index: 595741 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1655454 (Python Code)

Max Activating Token Index: 141