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

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

Neuron 3259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3984. Min Range: -5.3984

Max Act: 5.3984. Min Act: -0.0000

Data Index: 1060233 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.7307. Min Act: -0.0000

Data Index: 178381 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.6113. Min Act: -0.0000

Data Index: 1181318 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.9193. Min Act: -0.0000

Data Index: 33840 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.8836. Min Act: -0.0000

Data Index: 1223260 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.3617. Min Act: -0.0000

Data Index: 125503 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.3587. Min Act: -0.0000

Data Index: 314321 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.6954. Min Act: -0.0000

Data Index: 415259 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.3253. Min Act: -0.0000

Data Index: 549672 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.1472. Min Act: -0.0000

Data Index: 874423 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.2294. Min Act: -0.0000

Data Index: 320300 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.1671. Min Act: -0.0000

Data Index: 1338968 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.3213. Min Act: -0.0000

Data Index: 729617 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.4206. Min Act: -0.0000

Data Index: 860707 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.2352. Min Act: -0.0000

Data Index: 663291 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.3346. Min Act: -0.0000

Data Index: 1358091 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.2009. Min Act: -0.0000

Data Index: 792543 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 5.3984. Min Range: -5.3984

Max Act: 3.9983. Min Act: -0.0000

Data Index: 309305 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.1663. Min Act: -0.0000

Data Index: 1144453 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 5.3984. Min Range: -5.3984

Max Act: 4.1431. Min Act: -0.0000

Data Index: 1344152 (C4 (Web Text))

Max Activating Token Index: 509