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

Dataset: The Pile

Neuron 963 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: 1.1552. Min Range: -1.1552

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1471456 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1169464 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9351. Min Act: -0.0000

Data Index: 962403 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9147. Min Act: -0.0000

Data Index: 849256 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8539. Min Act: -0.0000

Data Index: 789293 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1773054 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9265. Min Act: -0.0000

Data Index: 720333 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1221115 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8218. Min Act: -0.0000

Data Index: 65294 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1686427 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1859802 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1663687 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9649. Min Act: -0.0000

Data Index: 449858 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8184. Min Act: -0.0000

Data Index: 11022 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9620. Min Act: -0.0000

Data Index: 988399 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8667. Min Act: -0.0000

Data Index: 996013 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1262228 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8509. Min Act: -0.0000

Data Index: 919998 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.9031. Min Act: -0.0000

Data Index: 954547 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8333. Min Act: -0.0000

Data Index: 373600 (The Pile)

Max Activating Token Index: 114