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

Dataset: The Pile

Neuron 4510 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: 1.2064. Min Range: -1.2064

Max Act: 1.2026. Min Act: -0.0000

Data Index: 577217 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.2064. Min Range: -1.2064

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1301155 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 1.2064. Min Range: -1.2064

Max Act: 1.0709. Min Act: -0.0000

Data Index: 412763 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 1.2064. Min Range: -1.2064

Max Act: 1.0381. Min Act: -0.0000

Data Index: 967138 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.2064. Min Range: -1.2064

Max Act: 1.0214. Min Act: -0.0000

Data Index: 776319 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9680. Min Act: -0.0000

Data Index: 90682 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9600. Min Act: -0.0000

Data Index: 257933 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1093337 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9202. Min Act: -0.0000

Data Index: 188186 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1133631 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1937489 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9275. Min Act: -0.0000

Data Index: 942379 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1600506 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1745044 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1983105 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1266746 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1889682 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1262332 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1104176 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 1.2064. Min Range: -1.2064

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1902657 (The Pile)

Max Activating Token Index: 870