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

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

Neuron 5208 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.5166. Min Act: -0.0002

Data Index: 540096 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.4731. Min Act: -0.0002

Data Index: 248705 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.4799. Min Act: -0.0002

Data Index: 1184120 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.4726. Min Act: -0.0002

Data Index: 297249 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.4057. Min Act: -0.0002

Data Index: 72248 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3854. Min Act: -0.0002

Data Index: 782602 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3668. Min Act: -0.0002

Data Index: 517118 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.4104. Min Act: -0.0002

Data Index: 1314178 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3985. Min Act: -0.0002

Data Index: 1207204 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3668. Min Act: -0.0002

Data Index: 819414 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3231. Min Act: -0.0002

Data Index: 1098759 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3688. Min Act: -0.0003

Data Index: 355128 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3071. Min Act: -0.0002

Data Index: 1110953 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3369. Min Act: -0.0002

Data Index: 1051093 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3212. Min Act: -0.0002

Data Index: 1226202 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3332. Min Act: -0.0002

Data Index: 1053796 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3258. Min Act: -0.0002

Data Index: 873983 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3211. Min Act: -0.0002

Data Index: 242893 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3097. Min Act: -0.0002

Data Index: 332022 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.3226. Min Act: -0.0002

Data Index: 60134 (C4 (Web Text))

Max Activating Token Index: 15