Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7602. Min Act: -0.0001

Data Index: 275585 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1143545 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7145. Min Act: -0.0000

Data Index: 132205 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6290. Min Act: -0.0001

Data Index: 369613 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6180. Min Act: -0.0001

Data Index: 803097 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6321. Min Act: -0.0001

Data Index: 580260 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6054. Min Act: -0.0001

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5736. Min Act: -0.0001

Data Index: 981997 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6092. Min Act: -0.0001

Data Index: 663060 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1249187 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1136098 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5499. Min Act: -0.0000

Data Index: 467168 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5485. Min Act: -0.0001

Data Index: 1640108 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5150. Min Act: -0.0000

Data Index: 860478 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5818. Min Act: -0.0001

Data Index: 687758 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5609. Min Act: -0.0001

Data Index: 482144 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1385086 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5443. Min Act: -0.0001

Data Index: 517886 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5725. Min Act: -0.0001

Data Index: 889619 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5551. Min Act: -0.0000

Data Index: 206486 (C4 (Web Text))

Max Activating Token Index: 423