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

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

Neuron 910 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.8764. Min Act: -0.0000

Data Index: 600323 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1425567 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3066. Min Act: -0.0000

Data Index: 408543 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3549. Min Act: -0.0000

Data Index: 454730 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1293166 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3323. Min Act: -0.0000

Data Index: 693080 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2957. Min Act: -0.0000

Data Index: 655198 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3642. Min Act: -0.0000

Data Index: 935066 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3264. Min Act: -0.0000

Data Index: 407363 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2650. Min Act: -0.0000

Data Index: 929124 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2662. Min Act: -0.0000

Data Index: 397066 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2813. Min Act: -0.0000

Data Index: 367705 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1072359 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1230436 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1309523 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.1897. Min Act: -0.0000

Data Index: 562688 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2243. Min Act: -0.0000

Data Index: 274127 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.1404. Min Act: -0.0000

Data Index: 212407 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1266529 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.1699. Min Act: -0.0000

Data Index: 794138 (C4 (Web Text))

Max Activating Token Index: 344