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

Dataset: The Pile

Neuron 53 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8904. Min Act: -0.0000

Data Index: 749890 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1139183 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1098115 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8855. Min Act: -0.0000

Data Index: 316586 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1451322 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8684. Min Act: -0.0000

Data Index: 572615 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1462400 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8436. Min Act: -0.0000

Data Index: 87302 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1690217 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1966613 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8376. Min Act: -0.0000

Data Index: 706674 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8319. Min Act: -0.0000

Data Index: 455012 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8298. Min Act: -0.0000

Data Index: 233947 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1155713 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7654. Min Act: -0.0000

Data Index: 809536 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7883. Min Act: -0.0000

Data Index: 236072 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7440. Min Act: -0.0000

Data Index: 735165 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1207254 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7289. Min Act: -0.0000

Data Index: 388270 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7459. Min Act: -0.0000

Data Index: 240950 (The Pile)

Max Activating Token Index: 171