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

Dataset: The Pile

Neuron 2803 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: 1.0374. Min Range: -1.0374

Max Act: 0.9618. Min Act: -0.0000

Data Index: 857732 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9728. Min Act: -0.0000

Data Index: 7716 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 1.0374. Min Range: -1.0374

Max Act: 1.0374. Min Act: -0.0000

Data Index: 18271 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.0374. Min Range: -1.0374

Max Act: 1.0259. Min Act: -0.0000

Data Index: 540007 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9530. Min Act: 0.0000

Data Index: 1223111 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9330. Min Act: -0.0000

Data Index: 593770 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9430. Min Act: -0.0000

Data Index: 799574 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1084935 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8811. Min Act: 0.0000

Data Index: 1311954 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1111321 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1041241 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1425860 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8561. Min Act: 0.0000

Data Index: 284780 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1230818 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9306. Min Act: -0.0000

Data Index: 132497 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8161. Min Act: -0.0000

Data Index: 662992 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1176383 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8298. Min Act: -0.0000

Data Index: 707720 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8799. Min Act: -0.0000

Data Index: 254713 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8513. Min Act: -0.0000

Data Index: 565922 (The Pile)

Max Activating Token Index: 81