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

Dataset: The Pile

Neuron 3549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2723. Min Act: -0.0000

Data Index: 411310 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2539. Min Act: -0.0000

Data Index: 983282 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1005708 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2286. Min Act: -0.0000

Data Index: 52206 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1902420 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2105. Min Act: -0.0000

Data Index: 871613 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2241. Min Act: -0.0000

Data Index: 934005 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1476087 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1520408 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2063. Min Act: -0.0000

Data Index: 429751 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1799. Min Act: -0.0000

Data Index: 847949 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1557631 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2030. Min Act: -0.0000

Data Index: 265484 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1079494 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2013. Min Act: -0.0000

Data Index: 268544 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1926428 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2074. Min Act: -0.0000

Data Index: 950754 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1923. Min Act: -0.0000

Data Index: 442030 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1850226 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1981. Min Act: -0.0000

Data Index: 728740 (The Pile)

Max Activating Token Index: 597