Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3764. Min Act: -0.0001

Data Index: 663970 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3534. Min Act: -0.0001

Data Index: 704401 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3454. Min Act: -0.0001

Data Index: 305918 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3381. Min Act: -0.0001

Data Index: 480172 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1111361 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3215. Min Act: -0.0001

Data Index: 911131 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3398. Min Act: -0.0001

Data Index: 764373 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1198701 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3141. Min Act: -0.0001

Data Index: 938527 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3032. Min Act: -0.0001

Data Index: 89354 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1071929 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3085. Min Act: -0.0001

Data Index: 96786 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3091. Min Act: -0.0001

Data Index: 260309 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3083. Min Act: -0.0001

Data Index: 417661 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1273888 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3263. Min Act: -0.0001

Data Index: 976088 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3130. Min Act: -0.0001

Data Index: 749999 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3123. Min Act: -0.0001

Data Index: 725181 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3000. Min Act: -0.0001

Data Index: 757355 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2912. Min Act: -0.0001

Data Index: 1257659 (C4 (Web Text))

Max Activating Token Index: 711