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

Dataset: The Pile

Neuron 2335 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: 1.1681. Min Range: -1.1681

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1800182 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1048923 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1229138 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9864. Min Act: -0.0000

Data Index: 77898 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.0593. Min Act: -0.0000

Data Index: 97280 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1227401 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9382. Min Act: -0.0000

Data Index: 953014 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9690. Min Act: -0.0000

Data Index: 108394 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9681. Min Act: -0.0000

Data Index: 63987 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9965. Min Act: -0.0000

Data Index: 276467 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1730058 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1383456 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1413767 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1240664 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9412. Min Act: -0.0000

Data Index: 859497 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1928955 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1807808 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8927. Min Act: -0.0000

Data Index: 502790 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1810925 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1009293 (The Pile)

Max Activating Token Index: 124