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

Dataset: The Pile

Neuron 1523 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: 0.3934. Min Range: -0.3934

Max Act: 0.3768. Min Act: -0.0000

Data Index: 807957 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3291. Min Act: -0.0000

Data Index: 956723 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3670. Min Act: -0.0000

Data Index: 294734 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1480197 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1525019 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1887579 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1774841 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3538. Min Act: -0.0000

Data Index: 420713 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3056. Min Act: -0.0000

Data Index: 297357 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3934. Min Act: -0.0000

Data Index: 615256 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3278. Min Act: -0.0000

Data Index: 36258 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3330. Min Act: -0.0000

Data Index: 607935 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3186. Min Act: -0.0000

Data Index: 808479 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1147532 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2970. Min Act: -0.0000

Data Index: 907272 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1942899 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3617. Min Act: -0.0000

Data Index: 966668 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3179. Min Act: -0.0000

Data Index: 523843 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3284. Min Act: -0.0000

Data Index: 564991 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3417. Min Act: -0.0000

Data Index: 772272 (The Pile)

Max Activating Token Index: 591