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

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

Neuron 3704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1130961 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3721. Min Act: -0.0000

Data Index: 969863 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3392. Min Act: -0.0000

Data Index: 849255 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1286515 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3483. Min Act: -0.0000

Data Index: 594870 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1251911 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3253. Min Act: -0.0000

Data Index: 805759 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3114. Min Act: -0.0000

Data Index: 43683 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3307. Min Act: -0.0000

Data Index: 830317 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3154. Min Act: -0.0000

Data Index: 642090 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1148431 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1092292 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3126. Min Act: -0.0000

Data Index: 740004 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3076. Min Act: -0.0000

Data Index: 258196 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3048. Min Act: -0.0000

Data Index: 134169 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1181314 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2555. Min Act: -0.0000

Data Index: 237735 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1252964 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1266701 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1075845 (C4 (Web Text))

Max Activating Token Index: 826