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

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

Neuron 4673 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2958. Min Act: -0.0001

Data Index: 914694 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.3145. Min Act: -0.0001

Data Index: 429878 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2866. Min Act: -0.0001

Data Index: 151440 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2388. Min Act: -0.0001

Data Index: 542074 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1955. Min Act: -0.0001

Data Index: 891951 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2143. Min Act: -0.0001

Data Index: 605043 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2153. Min Act: -0.0001

Data Index: 797727 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2034. Min Act: -0.0001

Data Index: 48986 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1263023 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1054919 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2287. Min Act: -0.0001

Data Index: 668985 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1007057 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2035. Min Act: -0.0001

Data Index: 330560 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1203273 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2003. Min Act: -0.0001

Data Index: 686128 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2065. Min Act: -0.0001

Data Index: 191111 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1997. Min Act: -0.0001

Data Index: 640794 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2127. Min Act: -0.0001

Data Index: 597419 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2056. Min Act: -0.0001

Data Index: 741342 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1121215 (C4 (Web Text))

Max Activating Token Index: 543