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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0024. Min Range: -1.0024

Max Act: 1.0024. Min Act: -0.0001

Data Index: 740753 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8841. Min Act: -0.0001

Data Index: 18490 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8751. Min Act: -0.0001

Data Index: 790385 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8473. Min Act: -0.0001

Data Index: 239034 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8937. Min Act: -0.0001

Data Index: 13175 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.9342. Min Act: -0.0001

Data Index: 477815 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7748. Min Act: -0.0001

Data Index: 178423 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8215. Min Act: -0.0001

Data Index: 613525 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7497. Min Act: -0.0001

Data Index: 601311 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7866. Min Act: -0.0001

Data Index: 751658 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1342924 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.8262. Min Act: -0.0001

Data Index: 75173 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7269. Min Act: -0.0001

Data Index: 284580 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1328009 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7395. Min Act: -0.0001

Data Index: 476790 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7664. Min Act: -0.0001

Data Index: 514431 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7085. Min Act: -0.0001

Data Index: 499117 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7729. Min Act: -0.0001

Data Index: 216731 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7185. Min Act: -0.0001

Data Index: 258637 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.0024. Min Range: -1.0024

Max Act: 0.7435. Min Act: -0.0001

Data Index: 509681 (C4 (Web Text))

Max Activating Token Index: 569