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

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

Neuron 409 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3991. Min Act: -0.0002

Data Index: 208029 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3559. Min Act: -0.0001

Data Index: 371858 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3891. Min Act: -0.0001

Data Index: 367040 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3409. Min Act: -0.0002

Data Index: 761142 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3496. Min Act: -0.0001

Data Index: 758700 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3723. Min Act: -0.0001

Data Index: 731598 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1603758 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3285. Min Act: -0.0001

Data Index: 837302 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3227. Min Act: -0.0002

Data Index: 115204 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3302. Min Act: -0.0002

Data Index: 153549 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2971. Min Act: -0.0002

Data Index: 741170 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3138. Min Act: -0.0001

Data Index: 536673 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1347405 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1162255 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3003. Min Act: -0.0002

Data Index: 919496 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3155. Min Act: -0.0001

Data Index: 454245 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2931. Min Act: -0.0001

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3125. Min Act: -0.0002

Data Index: 14686 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3230. Min Act: -0.0002

Data Index: 768602 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3010. Min Act: -0.0001

Data Index: 412670 (C4 (Web Text))

Max Activating Token Index: 748