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

Dataset: The Pile

Neuron 3174 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1462191 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1368727 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2898. Min Act: -0.0000

Data Index: 103010 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2525. Min Act: -0.0000

Data Index: 12532 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1960739 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1586. Min Act: -0.0000

Data Index: 906445 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2028. Min Act: -0.0000

Data Index: 810139 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1494740 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1674631 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1556. Min Act: -0.0000

Data Index: 911607 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1575090 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1306429 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1084003 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1247216 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1027. Min Act: -0.0000

Data Index: 513390 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1173. Min Act: -0.0000

Data Index: 995142 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1886125 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1317200 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1141891 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1240950 (The Pile)

Max Activating Token Index: 790