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

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

Neuron 4156 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: 0.2696. Min Range: -0.2696

Max Act: 0.2696. Min Act: -0.0002

Data Index: 802128 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2284. Min Act: -0.0002

Data Index: 1291083 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2317. Min Act: -0.0003

Data Index: 494750 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2306. Min Act: -0.0002

Data Index: 145864 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2305. Min Act: -0.0002

Data Index: 1056287 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2293. Min Act: -0.0002

Data Index: 486083 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2208. Min Act: -0.0002

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2240. Min Act: -0.0003

Data Index: 633510 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2235. Min Act: -0.0002

Data Index: 194735 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2190. Min Act: -0.0002

Data Index: 887301 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2187. Min Act: -0.0002

Data Index: 888670 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2162. Min Act: -0.0003

Data Index: 1349604 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2179. Min Act: -0.0002

Data Index: 812241 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2150. Min Act: -0.0002

Data Index: 395670 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2164. Min Act: -0.0002

Data Index: 1227164 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2108. Min Act: -0.0002

Data Index: 127935 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2144. Min Act: -0.0002

Data Index: 279943 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2113. Min Act: -0.0002

Data Index: 966407 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2105. Min Act: -0.0002

Data Index: 388398 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2088. Min Act: -0.0002

Data Index: 851100 (C4 (Web Text))

Max Activating Token Index: 120