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

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

Neuron 2087 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: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1144425 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1063301 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6678. Min Act: -0.0001

Data Index: 807761 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6344. Min Act: -0.0000

Data Index: 542059 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6230. Min Act: -0.0000

Data Index: 138506 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5778. Min Act: -0.0000

Data Index: 989216 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6142. Min Act: -0.0000

Data Index: 327809 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6106. Min Act: -0.0001

Data Index: 30093 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5957. Min Act: -0.0001

Data Index: 1330659 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5958. Min Act: -0.0000

Data Index: 650054 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5859. Min Act: -0.0001

Data Index: 486715 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5882. Min Act: -0.0000

Data Index: 136138 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5711. Min Act: -0.0000

Data Index: 536925 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5996. Min Act: -0.0001

Data Index: 383389 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5448. Min Act: -0.0000

Data Index: 224323 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1174440 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5792. Min Act: -0.0000

Data Index: 289408 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1108602 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5575. Min Act: -0.0001

Data Index: 637472 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1151282 (C4 (Web Text))

Max Activating Token Index: 807