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

Dataset: The Pile

Neuron 3448 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: 1.5115. Min Range: -1.5115

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1687641 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1181091 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1878683 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0994. Min Act: -0.0000

Data Index: 486170 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0983. Min Act: 0.0000

Data Index: 509169 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1013707 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1229984 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0162. Min Act: -0.0000

Data Index: 295169 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0153. Min Act: -0.0000

Data Index: 884524 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1557287 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0326. Min Act: 0.0000

Data Index: 474905 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1120753 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1307741 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8312. Min Act: 0.0000

Data Index: 949556 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1873049 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8725. Min Act: -0.0000

Data Index: 813452 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8845. Min Act: 0.0000

Data Index: 865423 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1084997 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9440. Min Act: -0.0000

Data Index: 176774 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1635949 (The Pile)

Max Activating Token Index: 463