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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4618. Min Act: -0.0000

Data Index: 47672 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4290. Min Act: -0.0000

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1172351 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3731. Min Act: -0.0000

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3717. Min Act: -0.0000

Data Index: 874929 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3979. Min Act: -0.0000

Data Index: 611538 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3907. Min Act: -0.0000

Data Index: 739710 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3739. Min Act: -0.0000

Data Index: 257519 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3884. Min Act: -0.0000

Data Index: 681027 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3758. Min Act: -0.0000

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1188926 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3709. Min Act: -0.0000

Data Index: 403209 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3730. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3557. Min Act: -0.0000

Data Index: 957554 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3316. Min Act: -0.0000

Data Index: 890183 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3641. Min Act: -0.0000

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3612. Min Act: -0.0000

Data Index: 964569 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1028666 (C4 (Web Text))

Max Activating Token Index: 836