Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4634 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.5327. Min Act: -0.0000

Data Index: 882188 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1155207 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.3861. Min Act: -0.0000

Data Index: 533161 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1311543 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.0313. Min Act: -0.0000

Data Index: 64984 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.5327. Min Range: -1.5327

Max Act: 1.0058. Min Act: -0.0000

Data Index: 902908 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1095793 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1007899 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.8450. Min Act: -0.0000

Data Index: 760032 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1053225 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.8484. Min Act: -0.0000

Data Index: 807982 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1031376 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.8348. Min Act: -0.0000

Data Index: 97678 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1059572 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.7908. Min Act: -0.0000

Data Index: 633650 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1188215 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.7063. Min Act: -0.0000

Data Index: 706054 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.7073. Min Act: -0.0000

Data Index: 80828 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.6814. Min Act: -0.0000

Data Index: 325358 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.5327. Min Range: -1.5327

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1231584 (C4 (Web Text))

Max Activating Token Index: 932