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

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

Neuron 95 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4961. Min Act: -0.0001

Data Index: 753551 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4424. Min Act: -0.0001

Data Index: 91566 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4062. Min Act: -0.0001

Data Index: 502576 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3545. Min Act: -0.0001

Data Index: 539261 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2734. Min Act: -0.0001

Data Index: 151760 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3816. Min Act: -0.0001

Data Index: 150596 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2556. Min Act: -0.0001

Data Index: 109403 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2402. Min Act: -0.0001

Data Index: 773900 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2289. Min Act: -0.0001

Data Index: 793277 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2855. Min Act: -0.0001

Data Index: 73341 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2036. Min Act: -0.0001

Data Index: 282492 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2614. Min Act: -0.0001

Data Index: 1040165 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3038. Min Act: -0.0001

Data Index: 1292472 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2429. Min Act: -0.0001

Data Index: 521030 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2020. Min Act: -0.0001

Data Index: 935505 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.1979. Min Act: -0.0001

Data Index: 97498 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.1621. Min Act: -0.0001

Data Index: 277815 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2605. Min Act: -0.0001

Data Index: 1031793 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.1250. Min Act: -0.0001

Data Index: 7266 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2269. Min Act: -0.0001

Data Index: 426874 (C4 (Web Text))

Max Activating Token Index: 779