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

Dataset: The Pile

Neuron 1712 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: 4.0167. Min Range: -4.0167

Max Act: 3.9484. Min Act: -0.0000

Data Index: 883296 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 4.0167. Min Range: -4.0167

Max Act: 4.0167. Min Act: -0.0000

Data Index: 1955704 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7783. Min Act: -0.0000

Data Index: 1106896 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8806. Min Act: -0.0000

Data Index: 22558 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8278. Min Act: -0.0000

Data Index: 1204088 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.6486. Min Act: -0.0000

Data Index: 1949303 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.6144. Min Act: -0.0000

Data Index: 871328 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8584. Min Act: -0.0000

Data Index: 758793 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7384. Min Act: -0.0000

Data Index: 1428411 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7298. Min Act: -0.0000

Data Index: 1144089 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7314. Min Act: -0.0000

Data Index: 1796238 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.5696. Min Act: -0.0000

Data Index: 254285 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.5710. Min Act: -0.0000

Data Index: 394920 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7232. Min Act: -0.0000

Data Index: 920287 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.3914. Min Act: -0.0000

Data Index: 1343552 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.5042. Min Act: -0.0000

Data Index: 834462 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.6443. Min Act: -0.0000

Data Index: 1246076 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.5945. Min Act: -0.0000

Data Index: 820248 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.2590. Min Act: -0.0000

Data Index: 846425 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.5746. Min Act: -0.0000

Data Index: 1252237 (The Pile)

Max Activating Token Index: 158