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

Dataset: The Pile

Neuron 2995 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: 3.2969. Min Range: -3.2969

Max Act: 3.1416. Min Act: -0.0000

Data Index: 1013831 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 3.2969. Min Range: -3.2969

Max Act: 3.2969. Min Act: -0.0000

Data Index: 1676052 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.6658. Min Act: -0.0000

Data Index: 1352591 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.8801. Min Act: -0.0000

Data Index: 1169116 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.5837. Min Act: -0.0000

Data Index: 220519 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.7571. Min Act: -0.0000

Data Index: 599927 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.8988. Min Act: -0.0000

Data Index: 1894882 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.7206. Min Act: -0.0000

Data Index: 1542481 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4783. Min Act: -0.0000

Data Index: 1666534 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.7350. Min Act: -0.0000

Data Index: 544096 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4792. Min Act: -0.0000

Data Index: 455207 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.6897. Min Act: -0.0000

Data Index: 1924312 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.7889. Min Act: -0.0000

Data Index: 529597 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4876. Min Act: -0.0000

Data Index: 317133 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4528. Min Act: -0.0000

Data Index: 147677 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.3250. Min Act: 0.0000

Data Index: 637353 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4342. Min Act: -0.0000

Data Index: 1151118 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.0792. Min Act: -0.0000

Data Index: 279301 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.4052. Min Act: -0.0000

Data Index: 259840 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 3.2969. Min Range: -3.2969

Max Act: 2.3773. Min Act: -0.0000

Data Index: 233284 (The Pile)

Max Activating Token Index: 590