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

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

Neuron 3882 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2937. Min Act: -0.0001

Data Index: 248423 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1019538 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2710. Min Act: -0.0001

Data Index: 1245919 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2407. Min Act: -0.0001

Data Index: 265609 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2415. Min Act: -0.0001

Data Index: 31328 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1350856 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2608. Min Act: -0.0001

Data Index: 67216 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2180. Min Act: -0.0001

Data Index: 913469 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2308. Min Act: -0.0001

Data Index: 41115 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2267. Min Act: -0.0001

Data Index: 373195 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2260. Min Act: -0.0000

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1065414 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2470. Min Act: -0.0001

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2143. Min Act: -0.0001

Data Index: 855413 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2197. Min Act: -0.0001

Data Index: 173630 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2177. Min Act: -0.0001

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2119. Min Act: -0.0000

Data Index: 730599 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2197. Min Act: -0.0001

Data Index: 386424 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1269864 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1370967 (Python Code)

Max Activating Token Index: 891