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

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

Neuron 4974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.4312. Min Act: -0.0000

Data Index: 1228466 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.2714. Min Act: -0.0001

Data Index: 165282 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.2911. Min Act: -0.0000

Data Index: 358266 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.9594. Min Act: -0.0000

Data Index: 1155520 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.0451. Min Act: -0.0000

Data Index: 21239 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.1414. Min Act: -0.0000

Data Index: 482744 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 2.4312. Min Range: -2.4312

Max Act: 2.0827. Min Act: -0.0000

Data Index: 264854 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1333873 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1115320 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8898. Min Act: -0.0001

Data Index: 1181220 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.7709. Min Act: -0.0001

Data Index: 657095 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8503. Min Act: -0.0000

Data Index: 46053 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8341. Min Act: -0.0000

Data Index: 1281273 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8374. Min Act: -0.0001

Data Index: 15814 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8213. Min Act: -0.0000

Data Index: 1300347 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8414. Min Act: -0.0000

Data Index: 63081 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8297. Min Act: -0.0000

Data Index: 787057 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.8070. Min Act: -0.0000

Data Index: 724445 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.7800. Min Act: -0.0000

Data Index: 597630 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.4312. Min Range: -2.4312

Max Act: 1.7643. Min Act: -0.0000

Data Index: 122313 (C4 (Web Text))

Max Activating Token Index: 724