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

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

Neuron 1263 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: 1.0153. Min Range: -1.0153

Max Act: 1.0153. Min Act: -0.0000

Data Index: 185290 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.8066. Min Act: 0.0001

Data Index: 723839 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1165938 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1073297 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1291071 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6483. Min Act: -0.0000

Data Index: 690416 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5859. Min Act: -0.0000

Data Index: 899007 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6433. Min Act: -0.0000

Data Index: 916467 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5460. Min Act: -0.0000

Data Index: 579984 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5703. Min Act: -0.0000

Data Index: 931212 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5850. Min Act: -0.0000

Data Index: 447061 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5820. Min Act: -0.0000

Data Index: 935224 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5696. Min Act: -0.0000

Data Index: 92023 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5454. Min Act: -0.0000

Data Index: 576050 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5711. Min Act: -0.0000

Data Index: 843405 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5508. Min Act: -0.0000

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5447. Min Act: 0.0001

Data Index: 1273983 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5659. Min Act: -0.0000

Data Index: 430444 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5612. Min Act: -0.0000

Data Index: 464428 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.5130. Min Act: -0.0000

Data Index: 238062 (C4 (Web Text))

Max Activating Token Index: 295