Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1487 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2830. Min Act: -0.0001

Data Index: 761504 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2768. Min Act: -0.0000

Data Index: 784065 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0000

Data Index: 469853 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1336453 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2632. Min Act: -0.0001

Data Index: 842207 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2598. Min Act: -0.0000

Data Index: 891164 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2567. Min Act: -0.0001

Data Index: 501689 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2467. Min Act: -0.0000

Data Index: 435485 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1258024 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2361. Min Act: -0.0000

Data Index: 89153 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2218. Min Act: -0.0001

Data Index: 657346 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1330587 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2221. Min Act: -0.0001

Data Index: 512993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2124. Min Act: -0.0000

Data Index: 322223 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2179. Min Act: -0.0000

Data Index: 832053 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2237. Min Act: -0.0000

Data Index: 449270 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2147. Min Act: -0.0000

Data Index: 423824 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2134. Min Act: -0.0001

Data Index: 60743 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2221. Min Act: -0.0001

Data Index: 815265 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2045. Min Act: -0.0001

Data Index: 679122 (C4 (Web Text))

Max Activating Token Index: 700