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

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

Neuron 3809 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3117. Min Range: -1.3117

Max Act: 1.3117. Min Act: -0.0001

Data Index: 886190 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.3117. Min Range: -1.3117

Max Act: 1.2765. Min Act: -0.0001

Data Index: 390490 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.3117. Min Range: -1.3117

Max Act: 1.1871. Min Act: -0.0001

Data Index: 720600 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.3117. Min Range: -1.3117

Max Act: 1.0990. Min Act: -0.0001

Data Index: 927269 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.9725. Min Act: -0.0001

Data Index: 1109512 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.9737. Min Act: -0.0001

Data Index: 1227268 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8780. Min Act: -0.0001

Data Index: 222704 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.9262. Min Act: -0.0001

Data Index: 505598 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.9848. Min Act: -0.0001

Data Index: 453231 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8659. Min Act: -0.0001

Data Index: 816327 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1332445 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8929. Min Act: -0.0001

Data Index: 196360 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.9497. Min Act: -0.0001

Data Index: 215857 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8732. Min Act: -0.0001

Data Index: 49358 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8504. Min Act: -0.0001

Data Index: 275445 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8547. Min Act: -0.0001

Data Index: 907701 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1340541 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8754. Min Act: -0.0001

Data Index: 1093609 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8705. Min Act: -0.0001

Data Index: 40811 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.3117. Min Range: -1.3117

Max Act: 0.8466. Min Act: -0.0001

Data Index: 732861 (C4 (Web Text))

Max Activating Token Index: 993