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

Dataset: The Pile

Neuron 1743 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: 0.4140. Min Range: -0.4140

Max Act: 0.4140. Min Act: -0.0000

Data Index: 649730 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1550017 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3378. Min Act: -0.0000

Data Index: 84975 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3272. Min Act: -0.0000

Data Index: 633294 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1748937 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3157. Min Act: -0.0000

Data Index: 641236 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3136. Min Act: -0.0000

Data Index: 578077 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2808. Min Act: -0.0000

Data Index: 952774 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3253. Min Act: -0.0000

Data Index: 732748 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2910. Min Act: -0.0000

Data Index: 534403 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2575. Min Act: -0.0000

Data Index: 555403 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1490719 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2634. Min Act: -0.0000

Data Index: 86867 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3011. Min Act: -0.0000

Data Index: 273561 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1351161 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2757. Min Act: -0.0000

Data Index: 483764 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2862. Min Act: -0.0000

Data Index: 345762 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1634200 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2880. Min Act: -0.0000

Data Index: 45475 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1371524 (The Pile)

Max Activating Token Index: 661