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

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

Neuron 92 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.2753. Min Act: -0.0000

Data Index: 24612 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8626. Min Act: -0.0000

Data Index: 238517 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8301. Min Act: -0.0001

Data Index: 657308 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8381. Min Act: -0.0001

Data Index: 1305283 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8881. Min Act: -0.0001

Data Index: 1332757 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8250. Min Act: -0.0001

Data Index: 415250 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8337. Min Act: -0.0001

Data Index: 1014179 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.7891. Min Act: -0.0000

Data Index: 182024 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.7252. Min Act: -0.0001

Data Index: 278702 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1056695 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1091299 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1170354 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.7188. Min Act: -0.0000

Data Index: 365133 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6717. Min Act: -0.0000

Data Index: 456056 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1252288 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6758. Min Act: -0.0000

Data Index: 614871 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6676. Min Act: -0.0001

Data Index: 627336 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6154. Min Act: -0.0001

Data Index: 638649 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.6079. Min Act: -0.0001

Data Index: 334941 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.5604. Min Act: -0.0001

Data Index: 851013 (C4 (Web Text))

Max Activating Token Index: 492