Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2424 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.3906. Min Act: -0.0002

Data Index: 350103 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.3273. Min Act: -0.0002

Data Index: 717172 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.3013. Min Act: -0.0002

Data Index: 401096 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.2653. Min Act: -0.0003

Data Index: 541593 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.2494. Min Act: -0.0003

Data Index: 481351 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.2034. Min Act: -0.0002

Data Index: 716412 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.2149. Min Act: -0.0002

Data Index: 586512 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1665. Min Act: -0.0003

Data Index: 1119393 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1590. Min Act: -0.0002

Data Index: 1226936 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1528. Min Act: -0.0002

Data Index: 878086 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1298. Min Act: -0.0002

Data Index: 156363 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1351. Min Act: -0.0002

Data Index: 471251 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1510. Min Act: -0.0002

Data Index: 1081476 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1395. Min Act: -0.0002

Data Index: 689613 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1384. Min Act: -0.0002

Data Index: 179900 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.0760. Min Act: -0.0002

Data Index: 426427 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1039. Min Act: -0.0002

Data Index: 509786 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1130. Min Act: -0.0002

Data Index: 1202886 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1028. Min Act: -0.0002

Data Index: 508235 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.0966. Min Act: -0.0002

Data Index: 391589 (C4 (Web Text))

Max Activating Token Index: 392