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

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

Neuron 2183 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4945. Min Act: -0.0003

Data Index: 316276 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5710. Min Act: -0.0003

Data Index: 592312 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4367. Min Act: -0.0003

Data Index: 213639 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5599. Min Act: -0.0003

Data Index: 491604 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5170. Min Act: -0.0003

Data Index: 1103751 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5261. Min Act: -0.0003

Data Index: 1199611 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5434. Min Act: -0.0003

Data Index: 716458 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5570. Min Act: -0.0003

Data Index: 1067384 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5026. Min Act: -0.0003

Data Index: 289778 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5300. Min Act: -0.0003

Data Index: 497836 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5474. Min Act: -0.0003

Data Index: 796507 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5495. Min Act: -0.0003

Data Index: 716371 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4949. Min Act: -0.0003

Data Index: 192970 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4996. Min Act: -0.0003

Data Index: 119046 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4476. Min Act: -0.0003

Data Index: 188641 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5408. Min Act: -0.0003

Data Index: 1322785 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4961. Min Act: -0.0003

Data Index: 774452 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4761. Min Act: -0.0003

Data Index: 862675 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5938. Min Act: -0.0003

Data Index: 481507 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4782. Min Act: -0.0003

Data Index: 939952 (C4 (Web Text))

Max Activating Token Index: 854