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

Dataset: The Pile

Neuron 1582 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: 1.4228. Min Range: -1.4228

Max Act: 1.4228. Min Act: -0.0000

Data Index: 884026 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1988930 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1855464 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1212673 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1588863 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9929. Min Act: -0.0000

Data Index: 956950 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1606541 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1149830 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1732996 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1650369 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9492. Min Act: -0.0000

Data Index: 49047 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1668689 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9064. Min Act: -0.0000

Data Index: 160169 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9261. Min Act: -0.0000

Data Index: 763532 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1992120 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1574855 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1114901 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1559211 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.8660. Min Act: -0.0000

Data Index: 606521 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9091. Min Act: -0.0000

Data Index: 917925 (The Pile)

Max Activating Token Index: 981