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

Dataset: The Pile

Neuron 3268 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1607255 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7095. Min Act: -0.0000

Data Index: 910596 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.7602. Min Act: -0.0000

Data Index: 623016 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1966655 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6064. Min Act: -0.0000

Data Index: 122065 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6296. Min Act: -0.0000

Data Index: 809380 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1268399 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1858935 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6124. Min Act: -0.0000

Data Index: 103487 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6076. Min Act: -0.0000

Data Index: 436506 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1482431 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1989610 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6120. Min Act: -0.0000

Data Index: 538230 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1241203 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5555. Min Act: -0.0000

Data Index: 410375 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5492. Min Act: -0.0000

Data Index: 817601 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1635956 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.6003. Min Act: -0.0000

Data Index: 693541 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5735. Min Act: -0.0000

Data Index: 979088 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.8144. Min Range: -0.8144

Max Act: 0.5721. Min Act: -0.0000

Data Index: 46608 (The Pile)

Max Activating Token Index: 358