Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1829 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.2078. Min Act: -0.0001

Data Index: 425521 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.1700. Min Act: -0.0001

Data Index: 962237 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.2078. Min Range: -1.2078

Max Act: 1.0649. Min Act: -0.0001

Data Index: 548633 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9479. Min Act: -0.0001

Data Index: 661904 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9097. Min Act: -0.0001

Data Index: 440996 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.9254. Min Act: -0.0001

Data Index: 87171 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8687. Min Act: -0.0001

Data Index: 172248 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8670. Min Act: -0.0001

Data Index: 1093247 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8614. Min Act: -0.0001

Data Index: 1139752 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8097. Min Act: -0.0001

Data Index: 404996 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8087. Min Act: -0.0001

Data Index: 31063 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8436. Min Act: -0.0001

Data Index: 1139523 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8344. Min Act: -0.0001

Data Index: 575445 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8482. Min Act: -0.0001

Data Index: 837570 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8505. Min Act: -0.0001

Data Index: 1345441 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.7843. Min Act: -0.0001

Data Index: 1138428 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.8722. Min Act: -0.0001

Data Index: 964276 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.7847. Min Act: -0.0001

Data Index: 327778 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.7546. Min Act: -0.0001

Data Index: 167084 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.2078. Min Range: -1.2078

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1021600 (C4 (Web Text))

Max Activating Token Index: 538