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

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

Neuron 5876 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: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 306837 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5136. Min Act: -0.0000

Data Index: 505236 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4842. Min Act: -0.0000

Data Index: 365493 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4686. Min Act: -0.0000

Data Index: 227037 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1326710 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4441. Min Act: -0.0000

Data Index: 792348 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1148583 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1019242 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4044. Min Act: -0.0000

Data Index: 863586 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3992. Min Act: -0.0000

Data Index: 96316 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3820. Min Act: -0.0000

Data Index: 702648 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4141. Min Act: -0.0000

Data Index: 304863 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3883. Min Act: -0.0000

Data Index: 929033 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4056. Min Act: -0.0000

Data Index: 458912 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3793. Min Act: -0.0000

Data Index: 864418 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3576. Min Act: 0.0000

Data Index: 963741 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3582. Min Act: -0.0000

Data Index: 584670 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3433. Min Act: -0.0000

Data Index: 207819 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3196. Min Act: -0.0000

Data Index: 327169 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3418. Min Act: -0.0000

Data Index: 263006 (C4 (Web Text))

Max Activating Token Index: 591