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

Dataset: The Pile

Neuron 3455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1489. Min Act: -0.0000

Data Index: 9554 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8501. Min Act: -0.0000

Data Index: 107912 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7436. Min Act: -0.0000

Data Index: 603053 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7209. Min Act: -0.0000

Data Index: 442201 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6476. Min Act: -0.0000

Data Index: 620193 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1608860 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1277020 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6343. Min Act: -0.0000

Data Index: 902384 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5431. Min Act: -0.0000

Data Index: 852537 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5973. Min Act: -0.0000

Data Index: 190221 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6105. Min Act: -0.0000

Data Index: 481476 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1114139 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1116588 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6107. Min Act: -0.0000

Data Index: 662113 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1554287 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1767054 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1888241 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5783. Min Act: -0.0000

Data Index: 793712 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1273963 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.5622. Min Act: -0.0000

Data Index: 692018 (The Pile)

Max Activating Token Index: 828