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

Dataset: The Pile

Neuron 3457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1470146 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1694178 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1126548 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0370. Min Act: -0.0000

Data Index: 868854 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0262. Min Act: -0.0000

Data Index: 537019 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0615. Min Act: -0.0000

Data Index: 169604 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8863. Min Act: -0.0000

Data Index: 463229 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9650. Min Act: -0.0000

Data Index: 30862 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9405. Min Act: -0.0000

Data Index: 421189 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1764117 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8930. Min Act: -0.0000

Data Index: 70198 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7956. Min Act: -0.0000

Data Index: 424575 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8678. Min Act: -0.0000

Data Index: 953283 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1839712 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1397840 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8108. Min Act: -0.0000

Data Index: 944021 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1035277 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8033. Min Act: -0.0000

Data Index: 939141 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1861366 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1143016 (The Pile)

Max Activating Token Index: 870