Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5515. Min Act: 0.0000

Data Index: 1816638 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1033950 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1327554 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4577. Min Act: 0.0000

Data Index: 354708 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1703660 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4195. Min Act: 0.0000

Data Index: 922125 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4090. Min Act: -0.0000

Data Index: 767677 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3830. Min Act: -0.0000

Data Index: 168042 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3867. Min Act: -0.0000

Data Index: 969286 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3841. Min Act: -0.0000

Data Index: 324148 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3512. Min Act: -0.0000

Data Index: 130326 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3840. Min Act: -0.0001

Data Index: 274044 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1711214 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3511. Min Act: -0.0001

Data Index: 155179 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1516171 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3674. Min Act: -0.0000

Data Index: 910395 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4005. Min Act: -0.0000

Data Index: 690311 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3269. Min Act: -0.0000

Data Index: 28911 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3778. Min Act: 0.0000

Data Index: 1423536 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3639. Min Act: -0.0000

Data Index: 652310 (The Pile)

Max Activating Token Index: 59