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

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

Neuron 2938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.3052. Min Act: -0.0001

Data Index: 62562 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.0419. Min Act: -0.0001

Data Index: 644752 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.0232. Min Act: -0.0001

Data Index: 1029715 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1252667 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1108932 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1277832 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9904. Min Act: -0.0001

Data Index: 257492 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9653. Min Act: -0.0001

Data Index: 57248 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9358. Min Act: -0.0001

Data Index: 272089 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9160. Min Act: -0.0001

Data Index: 915095 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8656. Min Act: -0.0001

Data Index: 868646 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8863. Min Act: -0.0001

Data Index: 1141362 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.0260. Min Act: -0.0001

Data Index: 1156295 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9903. Min Act: -0.0001

Data Index: 514111 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8355. Min Act: -0.0001

Data Index: 308462 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1256851 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8635. Min Act: -0.0001

Data Index: 247305 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8621. Min Act: -0.0001

Data Index: 254199 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8540. Min Act: -0.0001

Data Index: 639424 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8490. Min Act: -0.0001

Data Index: 267403 (C4 (Web Text))

Max Activating Token Index: 514