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

Dataset: The Pile

Neuron 551 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: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1662208 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3500. Min Act: -0.0000

Data Index: 116830 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1258243 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1562240 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1331938 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1576650 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1559486 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1905160 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1028036 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2867. Min Act: -0.0000

Data Index: 720910 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2854. Min Act: -0.0000

Data Index: 127626 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2656. Min Act: -0.0000

Data Index: 331597 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2999. Min Act: -0.0000

Data Index: 234928 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2523. Min Act: -0.0000

Data Index: 606010 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2624. Min Act: -0.0000

Data Index: 163033 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1621479 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1272053 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1740832 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2588. Min Act: -0.0000

Data Index: 730088 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2752. Min Act: -0.0000

Data Index: 22257 (The Pile)

Max Activating Token Index: 835