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

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

Neuron 5520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.4220. Min Act: -0.0000

Data Index: 254914 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.4225. Min Act: -0.0000

Data Index: 865914 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3005. Min Act: -0.0000

Data Index: 520215 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1104501 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.2749. Min Act: -0.0000

Data Index: 553057 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1119696 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.4225. Min Range: -1.4225

Max Act: 0.9885. Min Act: -0.0000

Data Index: 452761 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1773. Min Act: -0.0000

Data Index: 204276 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1562. Min Act: -0.0000

Data Index: 300578 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0847. Min Act: -0.0000

Data Index: 24949 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1067435 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1109864 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1330922 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0076. Min Act: -0.0000

Data Index: 519031 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.4225. Min Range: -1.4225

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1221493 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0451. Min Act: -0.0000

Data Index: 327470 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0384. Min Act: -0.0000

Data Index: 637442 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1107. Min Act: -0.0000

Data Index: 409335 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0303. Min Act: -0.0000

Data Index: 127275 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1167750 (C4 (Web Text))

Max Activating Token Index: 141