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

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

Neuron 251 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2268. Min Act: -0.0000

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.3507. Min Act: -0.0000

Data Index: 359601 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0411. Min Act: -0.0000

Data Index: 272675 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1094. Min Act: -0.0000

Data Index: 979224 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.8432. Min Act: -0.0000

Data Index: 183247 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0099. Min Act: -0.0000

Data Index: 494446 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.8416. Min Act: -0.0000

Data Index: 1300209 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.6881. Min Act: -0.0000

Data Index: 286669 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.5523. Min Act: -0.0000

Data Index: 626462 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.5316. Min Act: -0.0000

Data Index: 695896 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.7523. Min Act: -0.0000

Data Index: 69971 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.7318. Min Act: -0.0000

Data Index: 976316 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.6421. Min Act: -0.0000

Data Index: 596837 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.5714. Min Act: -0.0000

Data Index: 1217811 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.5739. Min Act: -0.0000

Data Index: 291983 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.5494. Min Act: -0.0000

Data Index: 60022 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.6582. Min Act: -0.0000

Data Index: 664329 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.6581. Min Act: -0.0000

Data Index: 698607 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.6324. Min Act: -0.0000

Data Index: 535148 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 3.3507. Min Range: -3.3507

Max Act: 2.4621. Min Act: -0.0000

Data Index: 863823 (C4 (Web Text))

Max Activating Token Index: 1019