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

Dataset: The Pile

Neuron 3500 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: 1.0133. Min Range: -1.0133

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1866492 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9285. Min Act: -0.0000

Data Index: 599214 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 1.0133. Min Range: -1.0133

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1048676 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1024313 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8545. Min Act: -0.0000

Data Index: 982263 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1097020 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7965. Min Act: -0.0000

Data Index: 2370 (The Pile)

Max Activating Token Index: 887

Text #7

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8719. Min Act: -0.0000

Data Index: 657100 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1524125 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1128495 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8550. Min Act: -0.0000

Data Index: 452882 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1021821 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1925932 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1099623 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8365. Min Act: -0.0000

Data Index: 67065 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7899. Min Act: -0.0000

Data Index: 962809 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8091. Min Act: -0.0000

Data Index: 261840 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1361861 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9286. Min Act: -0.0000

Data Index: 546447 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1625663 (The Pile)

Max Activating Token Index: 698