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

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

Neuron 4842 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: 1.6161. Min Range: -1.6161

Max Act: 1.6161. Min Act: -0.0000

Data Index: 856116 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.4623. Min Act: -0.0000

Data Index: 349669 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.4210. Min Act: -0.0000

Data Index: 680807 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1047441 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1270986 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2495. Min Act: -0.0000

Data Index: 12202 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1018669 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2882. Min Act: -0.0000

Data Index: 161445 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1120022 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1709. Min Act: -0.0000

Data Index: 414229 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1281830 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1760. Min Act: -0.0000

Data Index: 646107 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1741. Min Act: -0.0000

Data Index: 48680 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1277977 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1276759 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1161. Min Act: -0.0000

Data Index: 720057 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.0008. Min Act: -0.0000

Data Index: 450152 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.0945. Min Act: -0.0000

Data Index: 985153 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1403. Min Act: -0.0000

Data Index: 606407 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1331702 (C4 (Web Text))

Max Activating Token Index: 263