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

Dataset: The Pile

Neuron 1235 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: 1.2198. Min Range: -1.2198

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1921682 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1979028 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1481. Min Act: -0.0000

Data Index: 448132 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1394306 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1981775 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1998193 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1483439 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0300. Min Act: -0.0000

Data Index: 868235 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1498089 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1856024 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1935493 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9975. Min Act: -0.0000

Data Index: 835109 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9696. Min Act: -0.0000

Data Index: 479005 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1555538 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0041. Min Act: -0.0000

Data Index: 810724 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1075855 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9701. Min Act: -0.0000

Data Index: 242792 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9715. Min Act: -0.0000

Data Index: 629775 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1557665 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9750. Min Act: -0.0000

Data Index: 21062 (The Pile)

Max Activating Token Index: 352