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

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

Neuron 2041 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5768. Min Act: -0.0000

Data Index: 342232 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5064. Min Act: -0.0000

Data Index: 27532 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4135. Min Act: -0.0000

Data Index: 30511 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1302843 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4652. Min Act: -0.0000

Data Index: 338120 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4526. Min Act: -0.0000

Data Index: 1358045 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4329. Min Act: -0.0000

Data Index: 195162 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2926. Min Act: -0.0000

Data Index: 91968 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1218610 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3731. Min Act: -0.0000

Data Index: 643588 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2747. Min Act: -0.0000

Data Index: 857475 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1258642 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3121. Min Act: -0.0000

Data Index: 990576 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3142. Min Act: -0.0000

Data Index: 398300 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2195. Min Act: -0.0000

Data Index: 28324 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2917. Min Act: -0.0000

Data Index: 288643 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2907. Min Act: -0.0000

Data Index: 988396 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1334565 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2557. Min Act: -0.0000

Data Index: 526656 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3187. Min Act: -0.0000

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 610