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

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

Neuron 1045 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: 0.3005. Min Range: -0.3005

Max Act: 0.2924. Min Act: -0.0000

Data Index: 323202 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.3005. Min Act: -0.0000

Data Index: 428717 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1118911 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2350. Min Act: -0.0000

Data Index: 514097 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2392. Min Act: -0.0000

Data Index: 240413 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2084. Min Act: -0.0000

Data Index: 709776 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2021. Min Act: -0.0000

Data Index: 926329 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2001. Min Act: -0.0000

Data Index: 417958 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2091. Min Act: -0.0000

Data Index: 103307 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2302. Min Act: -0.0000

Data Index: 415847 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1063651 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1020436 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2100. Min Act: -0.0000

Data Index: 513740 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2001. Min Act: -0.0000

Data Index: 615946 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2144. Min Act: -0.0000

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2049. Min Act: -0.0000

Data Index: 21017 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.1975. Min Act: -0.0000

Data Index: 683818 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2043. Min Act: -0.0000

Data Index: 387177 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.1975. Min Act: -0.0000

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.1999. Min Act: -0.0000

Data Index: 88162 (C4 (Web Text))

Max Activating Token Index: 350