Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1881 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.7170. Min Act: -0.0000

Data Index: 1207529 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.5661. Min Act: -0.0000

Data Index: 209522 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.3238. Min Act: -0.0001

Data Index: 840837 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.1340. Min Act: -0.0001

Data Index: 332154 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.0585. Min Act: -0.0001

Data Index: 66291 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.7170. Min Range: -3.7170

Max Act: 3.0138. Min Act: -0.0001

Data Index: 165200 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.8580. Min Act: -0.0000

Data Index: 321358 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.9166. Min Act: -0.0000

Data Index: 1310648 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.9856. Min Act: -0.0001

Data Index: 1180384 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.9540. Min Act: -0.0001

Data Index: 652856 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.9192. Min Act: -0.0001

Data Index: 614836 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.7334. Min Act: -0.0001

Data Index: 92954 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.7189. Min Act: -0.0001

Data Index: 1231715 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.5592. Min Act: -0.0001

Data Index: 659542 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.8131. Min Act: -0.0001

Data Index: 1198807 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.5357. Min Act: -0.0001

Data Index: 1091828 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.9442. Min Act: -0.0001

Data Index: 477681 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.6414. Min Act: -0.0000

Data Index: 1045609 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.6151. Min Act: -0.0000

Data Index: 1193896 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.7170. Min Range: -3.7170

Max Act: 2.4321. Min Act: -0.0000

Data Index: 824948 (C4 (Web Text))

Max Activating Token Index: 672