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

Dataset: The Pile

Neuron 458 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: 1.2380. Min Range: -1.2380

Max Act: 1.2380. Min Act: -0.0000

Data Index: 214828 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0662. Min Act: -0.0000

Data Index: 544520 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8798. Min Act: -0.0000

Data Index: 998049 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8746. Min Act: -0.0000

Data Index: 739645 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8598. Min Act: -0.0000

Data Index: 13728 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1193521 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1973002 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8500. Min Act: -0.0000

Data Index: 224954 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1272995 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1537601 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1856895 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8006. Min Act: -0.0000

Data Index: 784333 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1223027 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8163. Min Act: -0.0000

Data Index: 182352 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8329. Min Act: -0.0000

Data Index: 559997 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.7706. Min Act: -0.0000

Data Index: 916437 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.7526. Min Act: -0.0000

Data Index: 957135 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8290. Min Act: -0.0000

Data Index: 834217 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1057647 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.7814. Min Act: -0.0000

Data Index: 436404 (The Pile)

Max Activating Token Index: 393