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

Dataset: The Pile

Neuron 421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.3813. Min Act: -0.0000

Data Index: 183927 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.5327. Min Act: -0.0000

Data Index: 1582801 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.1969. Min Act: -0.0000

Data Index: 543388 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1193797 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1497292 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.0941. Min Act: -0.0000

Data Index: 642201 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.2500. Min Act: -0.0000

Data Index: 1124055 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.0748. Min Act: -0.0000

Data Index: 944766 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.0712. Min Act: -0.0000

Data Index: 1374629 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.1998. Min Act: -0.0000

Data Index: 1867598 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.1996. Min Act: -0.0000

Data Index: 472406 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.1996. Min Act: -0.0000

Data Index: 876948 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.0221. Min Act: -0.0000

Data Index: 1450847 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.1233. Min Act: -0.0000

Data Index: 674242 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.0949. Min Act: -0.0000

Data Index: 384257 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 3.5327. Min Range: -3.5327

Max Act: 2.8947. Min Act: -0.0000

Data Index: 662061 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 3.5327. Min Range: -3.5327

Max Act: 3.2058. Min Act: -0.0000

Data Index: 139414 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 3.5327. Min Range: -3.5327

Max Act: 2.7296. Min Act: -0.0000

Data Index: 657856 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 3.5327. Min Range: -3.5327

Max Act: 2.7228. Min Act: -0.0000

Data Index: 997648 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 3.5327. Min Range: -3.5327

Max Act: 2.8177. Min Act: -0.0000

Data Index: 485882 (The Pile)

Max Activating Token Index: 41