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

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

Neuron 4514 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.9183. Min Act: -0.0002

Data Index: 1220174 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7902. Min Act: -0.0002

Data Index: 578298 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7590. Min Act: -0.0002

Data Index: 264221 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7365. Min Act: -0.0002

Data Index: 517881 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7334. Min Act: -0.0002

Data Index: 695112 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7346. Min Act: -0.0002

Data Index: 838699 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7274. Min Act: -0.0002

Data Index: 739927 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7114. Min Act: -0.0003

Data Index: 162863 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7127. Min Act: -0.0003

Data Index: 824638 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6791. Min Act: -0.0002

Data Index: 1148662 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.7010. Min Act: -0.0002

Data Index: 195992 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6544. Min Act: -0.0002

Data Index: 423359 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6530. Min Act: -0.0002

Data Index: 1308829 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6505. Min Act: -0.0002

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6839. Min Act: -0.0002

Data Index: 88117 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6485. Min Act: -0.0002

Data Index: 839935 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6042. Min Act: -0.0002

Data Index: 1204562 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.5987. Min Act: -0.0002

Data Index: 287930 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6203. Min Act: -0.0002

Data Index: 1306047 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.9183. Min Range: -0.9183

Max Act: 0.6382. Min Act: -0.0002

Data Index: 531848 (C4 (Web Text))

Max Activating Token Index: 681