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

Dataset: The Pile

Neuron 4156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1042424 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.5009. Min Act: -0.0000

Data Index: 224032 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1080008 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4867. Min Act: -0.0000

Data Index: 706390 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1074654 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1953617 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4608. Min Act: -0.0000

Data Index: 438099 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1420131 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1524076 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1046212 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.3779. Min Act: -0.0000

Data Index: 876005 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1582904 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1796761 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1438833 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.3968. Min Act: -0.0000

Data Index: 394019 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1492335 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4323. Min Act: -0.0000

Data Index: 707643 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.3806. Min Act: -0.0000

Data Index: 52363 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4152. Min Act: -0.0000

Data Index: 988246 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.5961. Min Range: -0.5961

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1129395 (The Pile)

Max Activating Token Index: 572