Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4349 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 11.6527. Min Range: -11.6527

Max Act: 11.6527. Min Act: -0.0000

Data Index: 1142129 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 11.6527. Min Range: -11.6527

Max Act: 11.3184. Min Act: -0.0000

Data Index: 562051 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 11.6527. Min Range: -11.6527

Max Act: 11.5305. Min Act: -0.0000

Data Index: 448806 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 11.6527. Min Range: -11.6527

Max Act: 11.1956. Min Act: -0.0000

Data Index: 1319961 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.5360. Min Act: -0.0000

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 11.6527. Min Range: -11.6527

Max Act: 11.1100. Min Act: -0.0000

Data Index: 495226 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.7914. Min Act: -0.0000

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.3218. Min Act: -0.0000

Data Index: 728345 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.1491. Min Act: -0.0000

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.1707. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 11.6527. Min Range: -11.6527

Max Act: 10.0740. Min Act: -0.0000

Data Index: 1353572 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.8595. Min Act: -0.0000

Data Index: 768984 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.0810. Min Act: -0.0000

Data Index: 32261 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.4968. Min Act: -0.0000

Data Index: 146813 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.1064. Min Act: -0.0000

Data Index: 809610 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.1026. Min Act: -0.0000

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 11.6527. Min Range: -11.6527

Max Act: 8.2053. Min Act: -0.0000

Data Index: 246510 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 11.6527. Min Range: -11.6527

Max Act: 9.1748. Min Act: -0.0000

Data Index: 981235 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 11.6527. Min Range: -11.6527

Max Act: 8.4678. Min Act: -0.0000

Data Index: 1012654 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 11.6527. Min Range: -11.6527

Max Act: 8.2693. Min Act: -0.0000

Data Index: 234359 (C4 (Web Text))

Max Activating Token Index: 488