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

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

Neuron 7 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1513. Min Act: -0.0002

Data Index: 526328 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.2405. Min Act: -0.0002

Data Index: 683365 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0578. Min Act: -0.0002

Data Index: 195277 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1191. Min Act: -0.0002

Data Index: 940532 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1350. Min Act: -0.0002

Data Index: 731129 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1632. Min Act: -0.0002

Data Index: 206824 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1825. Min Act: -0.0002

Data Index: 398447 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0199. Min Act: -0.0002

Data Index: 757401 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0982. Min Act: -0.0002

Data Index: 186866 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9078. Min Act: -0.0002

Data Index: 365132 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0486. Min Act: -0.0002

Data Index: 379259 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9764. Min Act: -0.0002

Data Index: 370704 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9996. Min Act: -0.0002

Data Index: 338827 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0432. Min Act: -0.0002

Data Index: 978542 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1105. Min Act: -0.0002

Data Index: 215746 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0987. Min Act: -0.0002

Data Index: 310027 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1372. Min Act: -0.0002

Data Index: 228559 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9653. Min Act: -0.0002

Data Index: 929201 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9567. Min Act: -0.0002

Data Index: 1038985 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0452. Min Act: -0.0002

Data Index: 799990 (C4 (Web Text))

Max Activating Token Index: 630