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

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

Neuron 463 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1206885 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1236344 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5751. Min Act: -0.0000

Data Index: 224809 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5469. Min Act: -0.0000

Data Index: 697088 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4814. Min Act: -0.0000

Data Index: 125214 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1235223 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4712. Min Act: -0.0000

Data Index: 687220 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1245271 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4389. Min Act: -0.0000

Data Index: 170255 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4265. Min Act: -0.0001

Data Index: 1003580 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4361. Min Act: -0.0000

Data Index: 805123 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4461. Min Act: -0.0000

Data Index: 444533 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4307. Min Act: -0.0000

Data Index: 115962 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4375. Min Act: -0.0000

Data Index: 517358 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4340. Min Act: -0.0000

Data Index: 24834 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4200. Min Act: -0.0001

Data Index: 972623 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1343025 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1221201 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4302. Min Act: -0.0000

Data Index: 121472 (C4 (Web Text))

Max Activating Token Index: 882