Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2912. Min Act: -0.0003

Data Index: 1131602 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2515. Min Act: -0.0003

Data Index: 314307 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2395. Min Act: -0.0003

Data Index: 898851 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2152. Min Act: -0.0003

Data Index: 1192724 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2178. Min Act: -0.0003

Data Index: 1113582 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2253. Min Act: -0.0003

Data Index: 569571 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2179. Min Act: -0.0003

Data Index: 1078786 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2183. Min Act: -0.0003

Data Index: 602371 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2220. Min Act: -0.0002

Data Index: 440215 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2101. Min Act: -0.0003

Data Index: 136788 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2177. Min Act: -0.0003

Data Index: 1120778 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2157. Min Act: -0.0003

Data Index: 231287 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2312. Min Act: -0.0003

Data Index: 1079657 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2238. Min Act: -0.0003

Data Index: 886277 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2067. Min Act: -0.0003

Data Index: 668161 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2215. Min Act: -0.0003

Data Index: 290420 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2070. Min Act: -0.0002

Data Index: 1274726 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2122. Min Act: -0.0003

Data Index: 393402 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2141. Min Act: -0.0003

Data Index: 1292180 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1145312 (C4 (Web Text))

Max Activating Token Index: 932