Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.2042. Min Act: -0.0001

Data Index: 521288 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1468. Min Act: -0.0001

Data Index: 400248 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1618. Min Act: -0.0001

Data Index: 952267 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1474. Min Act: -0.0001

Data Index: 557084 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1191. Min Act: -0.0001

Data Index: 865501 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1247. Min Act: -0.0001

Data Index: 563025 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1327. Min Act: -0.0001

Data Index: 162433 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1070494 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1240. Min Act: -0.0001

Data Index: 699101 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1227. Min Act: -0.0001

Data Index: 357489 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1232. Min Act: -0.0001

Data Index: 689794 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1143. Min Act: -0.0001

Data Index: 135228 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1074. Min Act: -0.0001

Data Index: 201276 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1090. Min Act: -0.0001

Data Index: 632259 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1121. Min Act: -0.0001

Data Index: 236850 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1099. Min Act: -0.0001

Data Index: 726778 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1271392 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1196. Min Act: -0.0001

Data Index: 183536 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1122. Min Act: -0.0001

Data Index: 998085 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1106929 (C4 (Web Text))

Max Activating Token Index: 942