Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.8981. Min Act: -0.0000

Data Index: 1646383 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.5347. Min Act: -0.0000

Data Index: 863064 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3493. Min Act: -0.0000

Data Index: 653098 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.4586. Min Act: -0.0000

Data Index: 1666481 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3529. Min Act: -0.0000

Data Index: 1477116 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3222. Min Act: -0.0000

Data Index: 1372976 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3110. Min Act: -0.0000

Data Index: 1765254 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.4527. Min Act: -0.0000

Data Index: 1922903 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1329. Min Act: -0.0000

Data Index: 1035070 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1432110 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.2454. Min Act: -0.0000

Data Index: 582241 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.0550. Min Act: -0.0000

Data Index: 322952 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.0857. Min Act: -0.0000

Data Index: 1095239 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1022. Min Act: -0.0000

Data Index: 1234917 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.9463. Min Act: -0.0000

Data Index: 1192085 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1051. Min Act: -0.0000

Data Index: 86714 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.2251. Min Act: -0.0000

Data Index: 1010249 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.0729. Min Act: -0.0000

Data Index: 1429774 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.9065. Min Act: -0.0000

Data Index: 301628 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1588. Min Act: -0.0000

Data Index: 631900 (The Pile)

Max Activating Token Index: 257