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

Dataset: The Pile

Neuron 3027 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: 0.9577. Min Range: -0.9577

Max Act: 0.9577. Min Act: -0.0000

Data Index: 786486 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.8639. Min Act: -0.0000

Data Index: 400025 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1084578 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6749. Min Act: -0.0000

Data Index: 819663 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.7175. Min Act: -0.0000

Data Index: 308585 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1011121 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6982. Min Act: -0.0000

Data Index: 535135 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1756833 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1162229 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1466953 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1539322 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1330113 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1464208 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1046309 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6687. Min Act: -0.0000

Data Index: 636385 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.5872. Min Act: -0.0000

Data Index: 327166 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6141. Min Act: -0.0000

Data Index: 859631 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1167207 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6131. Min Act: -0.0000

Data Index: 511023 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.5542. Min Act: -0.0000

Data Index: 908375 (The Pile)

Max Activating Token Index: 478