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

Dataset: The Pile

Neuron 2076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3529. Min Range: -4.3529

Max Act: 4.0951. Min Act: -0.0000

Data Index: 852329 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 4.3529. Min Range: -4.3529

Max Act: 4.3529. Min Act: -0.0000

Data Index: 1063734 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 4.3529. Min Range: -4.3529

Max Act: 4.0751. Min Act: -0.0000

Data Index: 1448030 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.8509. Min Act: -0.0000

Data Index: 1671164 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6533. Min Act: -0.0000

Data Index: 1122925 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.8882. Min Act: -0.0000

Data Index: 782721 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 4.3529. Min Range: -4.3529

Max Act: 4.0336. Min Act: -0.0000

Data Index: 1080680 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.5820. Min Act: -0.0000

Data Index: 980630 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6748. Min Act: -0.0000

Data Index: 708046 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6362. Min Act: -0.0000

Data Index: 1093647 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.5450. Min Act: -0.0000

Data Index: 1985849 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.9130. Min Act: -0.0000

Data Index: 1084037 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.5748. Min Act: -0.0000

Data Index: 1873547 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.5557. Min Act: -0.0000

Data Index: 1042332 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6775. Min Act: -0.0000

Data Index: 280488 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 4.3529. Min Range: -4.3529

Max Act: 4.0031. Min Act: -0.0000

Data Index: 727334 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6308. Min Act: -0.0000

Data Index: 399281 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6897. Min Act: -0.0000

Data Index: 162126 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.6624. Min Act: -0.0000

Data Index: 833253 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 4.3529. Min Range: -4.3529

Max Act: 3.4843. Min Act: -0.0000

Data Index: 349700 (The Pile)

Max Activating Token Index: 854