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

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

Neuron 2250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2767. Min Range: -3.2767

Max Act: 3.2767. Min Act: -0.0000

Data Index: 682171 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.2767. Min Range: -3.2767

Max Act: 3.0416. Min Act: -0.0000

Data Index: 481058 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.9891. Min Act: -0.0000

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.2767. Min Range: -3.2767

Max Act: 3.2184. Min Act: -0.0000

Data Index: 464469 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 3.2767. Min Range: -3.2767

Max Act: 3.0345. Min Act: -0.0000

Data Index: 631669 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 3.2767. Min Range: -3.2767

Max Act: 3.1478. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.8639. Min Act: -0.0000

Data Index: 77984 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.9046. Min Act: -0.0000

Data Index: 130203 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.8919. Min Act: -0.0000

Data Index: 216752 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.9158. Min Act: -0.0000

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.7611. Min Act: -0.0000

Data Index: 1124197 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.6089. Min Act: -0.0000

Data Index: 1049428 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 3.2767. Min Range: -3.2767

Max Act: 2.8624. Min Act: -0.0000

Data Index: 220331 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.9166. Min Act: -0.0000

Data Index: 519808 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.6367. Min Act: -0.0000

Data Index: 918497 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1185581 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.4336. Min Act: -0.0000

Data Index: 3814 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.6037. Min Act: -0.0000

Data Index: 634534 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.3988. Min Act: -0.0000

Data Index: 956650 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.2767. Min Range: -3.2767

Max Act: 1.3825. Min Act: -0.0000

Data Index: 800821 (C4 (Web Text))

Max Activating Token Index: 236