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

Dataset: The Pile

Neuron 3117 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: 3.2204. Min Range: -3.2204

Max Act: 3.2204. Min Act: -0.0000

Data Index: 1305580 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.2204. Min Range: -3.2204

Max Act: 3.1819. Min Act: -0.0000

Data Index: 1900892 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 3.2204. Min Range: -3.2204

Max Act: 3.1851. Min Act: -0.0000

Data Index: 1729243 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.9898. Min Act: -0.0000

Data Index: 1305848 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.9564. Min Act: -0.0000

Data Index: 1619340 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.7624. Min Act: -0.0000

Data Index: 1900377 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.7784. Min Act: -0.0000

Data Index: 1383027 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.8896. Min Act: -0.0000

Data Index: 1133761 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.7766. Min Act: -0.0000

Data Index: 234050 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6159. Min Act: -0.0000

Data Index: 1199463 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.7313. Min Act: -0.0000

Data Index: 885102 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.5847. Min Act: -0.0000

Data Index: 175177 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6871. Min Act: -0.0000

Data Index: 509211 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6795. Min Act: -0.0000

Data Index: 1730724 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6436. Min Act: -0.0000

Data Index: 85547 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6451. Min Act: -0.0000

Data Index: 1366315 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.7521. Min Act: -0.0000

Data Index: 730355 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.6204. Min Act: -0.0000

Data Index: 1007745 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.5936. Min Act: -0.0000

Data Index: 252477 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 3.2204. Min Range: -3.2204

Max Act: 2.5954. Min Act: -0.0000

Data Index: 1041323 (The Pile)

Max Activating Token Index: 248