Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0001

Data Index: 453093 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3073. Min Act: -0.0001

Data Index: 84791 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2978. Min Act: -0.0001

Data Index: 924634 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1322530 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3176. Min Act: -0.0001

Data Index: 223406 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3167. Min Act: -0.0001

Data Index: 187130 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2622. Min Act: -0.0001

Data Index: 320827 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2628. Min Act: -0.0001

Data Index: 883294 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2995. Min Act: -0.0001

Data Index: 632032 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1033507 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2976. Min Act: -0.0001

Data Index: 1125425 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1174010 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1105152 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2915. Min Act: -0.0001

Data Index: 1155213 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2904. Min Act: -0.0001

Data Index: 620915 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2798. Min Act: -0.0001

Data Index: 26015 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2835. Min Act: -0.0001

Data Index: 151785 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1058662 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2524. Min Act: -0.0001

Data Index: 954070 (C4 (Web Text))

Max Activating Token Index: 515