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

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

Neuron 1553 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6446. Min Act: -0.0001

Data Index: 572604 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.7062. Min Act: -0.0001

Data Index: 876936 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6686. Min Act: -0.0001

Data Index: 997804 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.7261. Min Act: -0.0001

Data Index: 730097 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6318. Min Act: -0.0001

Data Index: 669356 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1306522 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1267570 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5605. Min Act: -0.0001

Data Index: 116047 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.4606. Min Act: -0.0001

Data Index: 960190 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5582. Min Act: -0.0001

Data Index: 408016 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5536. Min Act: -0.0001

Data Index: 1270089 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.4699. Min Act: -0.0001

Data Index: 125879 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5263. Min Act: -0.0001

Data Index: 414896 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5197. Min Act: -0.0001

Data Index: 967294 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5149. Min Act: -0.0001

Data Index: 440734 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5130. Min Act: -0.0001

Data Index: 678292 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5191. Min Act: -0.0001

Data Index: 319182 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5253. Min Act: -0.0001

Data Index: 7501 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.4748. Min Act: -0.0001

Data Index: 306656 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5161. Min Act: -0.0001

Data Index: 257371 (C4 (Web Text))

Max Activating Token Index: 178