Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1036 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3620. Min Range: -2.3620

Max Act: 2.3620. Min Act: -0.0000

Data Index: 894166 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.9645. Min Act: -0.0000

Data Index: 1016667 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 2.3620. Min Range: -2.3620

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1021250 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.3620. Min Range: -2.3620

Max Act: 2.0482. Min Act: -0.0000

Data Index: 294160 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.9349. Min Act: -0.0000

Data Index: 623374 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.9370. Min Act: -0.0000

Data Index: 126518 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 2.3620. Min Range: -2.3620

Max Act: 2.0050. Min Act: -0.0000

Data Index: 913355 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.6870. Min Act: -0.0000

Data Index: 246988 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1127324 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.7602. Min Act: -0.0000

Data Index: 255644 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.7548. Min Act: -0.0000

Data Index: 1111086 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.8616. Min Act: -0.0000

Data Index: 230113 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.5296. Min Act: -0.0000

Data Index: 713361 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1104706 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.7414. Min Act: -0.0000

Data Index: 558827 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.5405. Min Act: -0.0000

Data Index: 3519 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.6034. Min Act: -0.0000

Data Index: 457819 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.4970. Min Act: -0.0000

Data Index: 549109 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.6646. Min Act: -0.0000

Data Index: 662909 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 2.3620. Min Range: -2.3620

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1059927 (C4 (Web Text))

Max Activating Token Index: 89