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

Dataset: The Pile

Neuron 945 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: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 844654 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1595982 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1044908 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5070. Min Act: -0.0000

Data Index: 869870 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1961830 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5027. Min Act: -0.0000

Data Index: 141669 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4935. Min Act: -0.0000

Data Index: 620445 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1581502 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5174. Min Act: -0.0000

Data Index: 84551 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4802. Min Act: -0.0000

Data Index: 370952 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1614498 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1656033 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1039371 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4435. Min Act: -0.0000

Data Index: 429375 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4388. Min Act: -0.0000

Data Index: 770376 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1446886 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4488. Min Act: -0.0000

Data Index: 950848 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1712706 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1393655 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4813. Min Act: -0.0000

Data Index: 201116 (The Pile)

Max Activating Token Index: 985