Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2734. Min Act: -0.0001

Data Index: 611648 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1232515 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2226. Min Act: -0.0001

Data Index: 333649 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1189727 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2288. Min Act: -0.0001

Data Index: 391694 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2366. Min Act: -0.0001

Data Index: 378457 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2301. Min Act: -0.0001

Data Index: 580336 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2286. Min Act: -0.0001

Data Index: 478535 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2277. Min Act: -0.0001

Data Index: 5838 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2256. Min Act: -0.0001

Data Index: 866949 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1066041 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1225292 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2136. Min Act: -0.0001

Data Index: 464983 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2137. Min Act: -0.0001

Data Index: 948613 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2085. Min Act: -0.0001

Data Index: 487196 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2077. Min Act: -0.0001

Data Index: 555337 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2073. Min Act: -0.0001

Data Index: 521153 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2060. Min Act: -0.0001

Data Index: 611088 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1349943 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2018. Min Act: -0.0001

Data Index: 190812 (C4 (Web Text))

Max Activating Token Index: 471