Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2376 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1410364 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1808. Min Act: -0.0000

Data Index: 116238 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0124. Min Act: -0.0000

Data Index: 203382 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9578. Min Act: -0.0000

Data Index: 853110 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9529. Min Act: -0.0000

Data Index: 610292 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1093. Min Act: -0.0000

Data Index: 375619 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0392. Min Act: -0.0000

Data Index: 468827 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1990785 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9257. Min Act: -0.0000

Data Index: 540904 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1231633 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8388. Min Act: -0.0000

Data Index: 155450 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1880342 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1823120 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8439. Min Act: -0.0000

Data Index: 945145 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8549. Min Act: -0.0000

Data Index: 993671 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1939550 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9069. Min Act: -0.0000

Data Index: 385237 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1554371 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1783588 (The Pile)

Max Activating Token Index: 543

Text #19

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8841. Min Act: -0.0000

Data Index: 782832 (The Pile)

Max Activating Token Index: 136