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

Dataset: The Pile

Neuron 2667 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8491. Min Act: -0.0000

Data Index: 303574 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1647955 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7554. Min Act: -0.0000

Data Index: 264599 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1303232 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7334. Min Act: -0.0000

Data Index: 880859 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1525224 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6968. Min Act: -0.0000

Data Index: 828991 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6852. Min Act: -0.0000

Data Index: 683552 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6997. Min Act: -0.0000

Data Index: 623750 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1596296 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1865696 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1204083 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1404614 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1097230 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6094. Min Act: -0.0000

Data Index: 488622 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.5983. Min Act: -0.0000

Data Index: 561166 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6733. Min Act: -0.0000

Data Index: 570219 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6325. Min Act: -0.0000

Data Index: 438251 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1974702 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6334. Min Act: -0.0000

Data Index: 520105 (The Pile)

Max Activating Token Index: 303