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

Dataset: The Pile

Neuron 2320 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: 0.9559. Min Range: -0.9559

Max Act: 0.9559. Min Act: -0.0000

Data Index: 408912 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1502570 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8362. Min Act: -0.0000

Data Index: 474436 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8715. Min Act: -0.0000

Data Index: 791422 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1646287 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7801. Min Act: -0.0000

Data Index: 213256 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7958. Min Act: -0.0000

Data Index: 776814 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.8125. Min Act: -0.0000

Data Index: 238109 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1647384 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7775. Min Act: -0.0000

Data Index: 789701 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1973069 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7061. Min Act: -0.0000

Data Index: 722198 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7233. Min Act: -0.0000

Data Index: 203745 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7044. Min Act: -0.0000

Data Index: 623808 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7660. Min Act: -0.0000

Data Index: 67713 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1886245 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1996246 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1138731 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7369. Min Act: -0.0000

Data Index: 29752 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.9559. Min Range: -0.9559

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1368216 (The Pile)

Max Activating Token Index: 1000