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

Dataset: The Pile

Neuron 1470 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: 1.4982. Min Range: -1.4982

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1609033 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1720459 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1943565 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3945. Min Act: -0.0000

Data Index: 708971 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1486859 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1629086 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3348. Min Act: -0.0000

Data Index: 618708 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3230. Min Act: -0.0000

Data Index: 252430 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3533. Min Act: -0.0000

Data Index: 188101 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1249143 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3115. Min Act: -0.0000

Data Index: 728857 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2749. Min Act: -0.0000

Data Index: 46796 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1543015 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3467. Min Act: -0.0000

Data Index: 680798 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1165532 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1576384 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1221620 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1241737 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2565. Min Act: -0.0000

Data Index: 566703 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1298434 (The Pile)

Max Activating Token Index: 515