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

Dataset: The Pile

Neuron 3716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9706. Min Act: -0.0000

Data Index: 306175 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9535. Min Act: -0.0000

Data Index: 766783 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1187211 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1059386 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1052221 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1568527 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1414582 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1362115 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8747. Min Act: -0.0000

Data Index: 228160 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1285827 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8460. Min Act: -0.0000

Data Index: 196388 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8887. Min Act: -0.0000

Data Index: 533168 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1066838 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1878927 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8485. Min Act: -0.0000

Data Index: 86674 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1492446 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1891257 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8157. Min Act: 0.0000

Data Index: 139169 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7862. Min Act: -0.0000

Data Index: 998776 (The Pile)

Max Activating Token Index: 45

Text #19

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7881. Min Act: -0.0000

Data Index: 379780 (The Pile)

Max Activating Token Index: 456