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

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

Neuron 1557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4273. Min Act: -0.0000

Data Index: 927124 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4212. Min Act: -0.0000

Data Index: 471293 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2912. Min Act: -0.0000

Data Index: 631623 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1052998 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2755. Min Act: -0.0000

Data Index: 706244 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2599. Min Act: -0.0000

Data Index: 378126 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2496. Min Act: -0.0000

Data Index: 875546 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1275 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2605. Min Act: -0.0000

Data Index: 411502 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2405. Min Act: -0.0000

Data Index: 402644 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2422. Min Act: -0.0000

Data Index: 552118 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1250019 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2104. Min Act: -0.0000

Data Index: 219765 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2142. Min Act: -0.0000

Data Index: 9853 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2020. Min Act: -0.0000

Data Index: 959807 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2295. Min Act: -0.0000

Data Index: 381302 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1026423 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.2050. Min Act: -0.0000

Data Index: 676298 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.1902. Min Act: -0.0001

Data Index: 275175 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.1946. Min Act: -0.0000

Data Index: 656455 (C4 (Web Text))

Max Activating Token Index: 397