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

Dataset: The Pile

Neuron 4298 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.8120. Min Act: -0.0000

Data Index: 356787 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1459135 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1158416 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6795. Min Act: -0.0000

Data Index: 363550 (The Pile)

Max Activating Token Index: 705

Text #4

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7327. Min Act: -0.0000

Data Index: 24482 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7836. Min Act: -0.0000

Data Index: 440551 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7741. Min Act: -0.0000

Data Index: 621549 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1856193 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6994. Min Act: -0.0000

Data Index: 232312 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1959655 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1428214 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7000. Min Act: -0.0000

Data Index: 261607 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7285. Min Act: -0.0000

Data Index: 836729 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6897. Min Act: -0.0000

Data Index: 649562 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6664. Min Act: -0.0000

Data Index: 391608 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6574. Min Act: -0.0000

Data Index: 803226 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1828264 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1105645 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1388217 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6395. Min Act: -0.0000

Data Index: 856740 (The Pile)

Max Activating Token Index: 674