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

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

Neuron 2107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.7102. Min Act: -0.0001

Data Index: 375778 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.4444. Min Act: -0.0001

Data Index: 1123529 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.4968. Min Act: -0.0001

Data Index: 286737 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.3336. Min Act: -0.0001

Data Index: 443056 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.3156. Min Act: -0.0001

Data Index: 793238 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.3351. Min Act: -0.0001

Data Index: 214636 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2326. Min Act: -0.0001

Data Index: 387890 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.3059. Min Act: -0.0001

Data Index: 139235 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2098. Min Act: -0.0001

Data Index: 395952 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1127785 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2331. Min Act: -0.0001

Data Index: 370657 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.1591. Min Act: -0.0001

Data Index: 211101 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2475. Min Act: -0.0001

Data Index: 149530 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.1051. Min Act: -0.0001

Data Index: 43197 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.0978. Min Act: -0.0001

Data Index: 239302 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.0577. Min Act: -0.0001

Data Index: 260975 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.1866. Min Act: -0.0001

Data Index: 1013787 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.1147. Min Act: -0.0001

Data Index: 998784 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.2220. Min Act: -0.0001

Data Index: 162356 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.7102. Min Range: -1.7102

Max Act: 1.1293. Min Act: -0.0001

Data Index: 90726 (C4 (Web Text))

Max Activating Token Index: 474