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

Dataset: The Pile

Neuron 1621 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: 0.5237. Min Range: -0.5237

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1780972 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1100965 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1620999 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4594. Min Act: -0.0000

Data Index: 504742 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4407. Min Act: -0.0000

Data Index: 533707 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4217. Min Act: -0.0000

Data Index: 646869 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4219. Min Act: 0.0000

Data Index: 1136924 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1690712 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4171. Min Act: -0.0000

Data Index: 536644 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1464393 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1773345 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1554090 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4351. Min Act: -0.0000

Data Index: 281277 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4134. Min Act: -0.0000

Data Index: 565530 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1118565 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4085. Min Act: -0.0000

Data Index: 86757 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4102. Min Act: -0.0000

Data Index: 416494 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1382925 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3893. Min Act: -0.0000

Data Index: 330021 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1728266 (The Pile)

Max Activating Token Index: 515