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

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

Neuron 1115 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: 0.7497. Min Range: -0.7497

Max Act: 0.7497. Min Act: -0.0000

Data Index: 220121 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6315. Min Act: -0.0000

Data Index: 246380 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6289. Min Act: -0.0000

Data Index: 264153 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5885. Min Act: -0.0000

Data Index: 683999 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1071969 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4668. Min Act: -0.0000

Data Index: 474424 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4620. Min Act: -0.0000

Data Index: 403122 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4624. Min Act: -0.0000

Data Index: 431542 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4780. Min Act: -0.0000

Data Index: 720087 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4529. Min Act: -0.0000

Data Index: 665570 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1267250 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4173. Min Act: -0.0000

Data Index: 590910 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4171. Min Act: -0.0000

Data Index: 452117 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.3936. Min Act: -0.0000

Data Index: 429509 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.3950. Min Act: -0.0000

Data Index: 267159 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4071. Min Act: -0.0000

Data Index: 358847 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1017434 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.3828. Min Act: -0.0000

Data Index: 820306 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.3945. Min Act: -0.0000

Data Index: 358340 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.4071. Min Act: -0.0000

Data Index: 707996 (C4 (Web Text))

Max Activating Token Index: 290