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

Dataset: The Pile

Neuron 1002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1443965 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.4103. Min Act: -0.0000

Data Index: 171771 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1102733 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3363. Min Act: -0.0000

Data Index: 259625 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1093779 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1900914 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1814982 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1858608 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1155250 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2487. Min Act: -0.0000

Data Index: 401573 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2832. Min Act: -0.0000

Data Index: 720071 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1994798 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2713. Min Act: -0.0000

Data Index: 359742 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1720801 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2605. Min Act: -0.0000

Data Index: 400603 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2436. Min Act: -0.0000

Data Index: 143324 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1969272 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2400. Min Act: -0.0000

Data Index: 121448 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1477701 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.4137. Min Range: -0.4137

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1356004 (The Pile)

Max Activating Token Index: 872