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

Dataset: The Pile

Neuron 1418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5663. Min Act: -0.0000

Data Index: 510262 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5548. Min Act: -0.0000

Data Index: 926579 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1132291 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5244. Min Act: -0.0000

Data Index: 731529 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1607753 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1843999 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4950. Min Act: -0.0000

Data Index: 127912 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1584493 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1766330 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1908039 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4440. Min Act: -0.0000

Data Index: 924733 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4587. Min Act: -0.0000

Data Index: 924854 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1581943 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4462. Min Act: -0.0000

Data Index: 786993 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4448. Min Act: -0.0000

Data Index: 865052 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4454. Min Act: -0.0000

Data Index: 710479 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1242651 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4405. Min Act: -0.0000

Data Index: 664453 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4353. Min Act: -0.0000

Data Index: 853669 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4471. Min Act: -0.0000

Data Index: 861714 (The Pile)

Max Activating Token Index: 184