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

Dataset: The Pile

Neuron 2259 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: 0.5547. Min Range: -0.5547

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1250456 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5140. Min Act: -0.0000

Data Index: 635398 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1527478 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1414861 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1190987 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4092. Min Act: -0.0000

Data Index: 966035 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4560. Min Act: -0.0000

Data Index: 331354 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1070111 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4391. Min Act: -0.0000

Data Index: 919866 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1417622 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1147935 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4234. Min Act: -0.0000

Data Index: 151927 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1850706 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4337. Min Act: -0.0000

Data Index: 55422 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1601130 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4607. Min Act: -0.0000

Data Index: 471057 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4231. Min Act: -0.0000

Data Index: 313011 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3798. Min Act: -0.0000

Data Index: 22998 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4188. Min Act: -0.0000

Data Index: 126867 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4211. Min Act: -0.0000

Data Index: 11009 (The Pile)

Max Activating Token Index: 67