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

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

Neuron 4809 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.3965. Min Act: -0.0000

Data Index: 266841 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.1619. Min Act: -0.0000

Data Index: 382276 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.2853. Min Act: -0.0000

Data Index: 228164 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.2590. Min Act: -0.0000

Data Index: 1347801 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.1261. Min Act: -0.0000

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.3639. Min Act: -0.0000

Data Index: 251624 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1130363 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.9129. Min Act: -0.0000

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.3965. Min Range: -2.3965

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.8745. Min Act: -0.0000

Data Index: 717580 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.9417. Min Act: -0.0000

Data Index: 339638 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.8780. Min Act: -0.0000

Data Index: 1014278 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.8888. Min Act: -0.0000

Data Index: 112335 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.8679. Min Act: -0.0000

Data Index: 1303050 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.9688. Min Act: -0.0000

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.7612. Min Act: -0.0000

Data Index: 607676 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.7407. Min Act: -0.0000

Data Index: 155677 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.8313. Min Act: -0.0000

Data Index: 864202 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.7449. Min Act: -0.0000

Data Index: 410019 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.3965. Min Range: -2.3965

Max Act: 1.9224. Min Act: -0.0000

Data Index: 698592 (C4 (Web Text))

Max Activating Token Index: 589