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

Dataset: The Pile

Neuron 2378 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1823389 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7337. Min Act: -0.0000

Data Index: 80872 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6600. Min Act: -0.0000

Data Index: 110797 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1215314 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5573. Min Act: -0.0000

Data Index: 387701 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4643. Min Act: -0.0000

Data Index: 88465 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4427. Min Act: -0.0000

Data Index: 561306 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4587. Min Act: -0.0000

Data Index: 795381 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1166574 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1644367 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1229017 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1617741 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1602814 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.3709. Min Act: -0.0000

Data Index: 726097 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1344044 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.3842. Min Act: -0.0000

Data Index: 75231 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1762168 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1427747 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1448629 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1728644 (The Pile)

Max Activating Token Index: 336