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

Dataset: The Pile

Neuron 1385 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7778. Min Act: -0.0000

Data Index: 920356 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.8108. Min Act: -0.0000

Data Index: 155581 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1733802 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1196208 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1777596 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6686. Min Act: -0.0000

Data Index: 991498 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6209. Min Act: -0.0000

Data Index: 853990 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.5557. Min Act: -0.0000

Data Index: 154810 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.5421. Min Act: -0.0000

Data Index: 701742 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.5800. Min Act: -0.0000

Data Index: 597766 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4918. Min Act: -0.0000

Data Index: 35005 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4294. Min Act: -0.0000

Data Index: 814856 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1765404 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4145. Min Act: 0.0000

Data Index: 1428241 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1440895 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4263. Min Act: -0.0000

Data Index: 307975 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1542571 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4091. Min Act: -0.0000

Data Index: 518654 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.4039. Min Act: -0.0000

Data Index: 813622 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.3976. Min Act: -0.0000

Data Index: 706791 (The Pile)

Max Activating Token Index: 254