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

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

Neuron 1259 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1652172 (Python Code)

Max Activating Token Index: 722

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2610. Min Act: -0.0001

Data Index: 853705 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2473. Min Act: -0.0001

Data Index: 578576 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2371. Min Act: -0.0001

Data Index: 665628 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2339. Min Act: -0.0001

Data Index: 448995 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2292. Min Act: -0.0001

Data Index: 661053 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2356. Min Act: -0.0001

Data Index: 993141 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2311. Min Act: -0.0001

Data Index: 916556 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2149. Min Act: -0.0001

Data Index: 538317 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1010344 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2048. Min Act: -0.0001

Data Index: 417199 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2083. Min Act: -0.0001

Data Index: 18924 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2058. Min Act: -0.0001

Data Index: 187408 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2268. Min Act: -0.0001

Data Index: 250017 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2057. Min Act: -0.0001

Data Index: 422487 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2208. Min Act: -0.0001

Data Index: 920235 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2149. Min Act: -0.0001

Data Index: 382192 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2160. Min Act: -0.0001

Data Index: 120137 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2090. Min Act: -0.0001

Data Index: 692181 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1921. Min Act: -0.0001

Data Index: 783670 (C4 (Web Text))

Max Activating Token Index: 918