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

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

Neuron 2772 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: 1.6965. Min Range: -1.6965

Max Act: 1.6965. Min Act: -0.0003

Data Index: 41425 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6307. Min Act: -0.0003

Data Index: 1108746 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5678. Min Act: -0.0002

Data Index: 822864 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5208. Min Act: -0.0002

Data Index: 720566 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5373. Min Act: -0.0002

Data Index: 1346227 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4990. Min Act: -0.0002

Data Index: 767398 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5312. Min Act: -0.0002

Data Index: 835936 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5537. Min Act: -0.0002

Data Index: 133755 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.5312. Min Act: -0.0003

Data Index: 28341 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4846. Min Act: -0.0002

Data Index: 1238764 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4875. Min Act: -0.0003

Data Index: 1058160 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4705. Min Act: -0.0002

Data Index: 535033 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4438. Min Act: -0.0002

Data Index: 527453 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4886. Min Act: -0.0002

Data Index: 1100161 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4562. Min Act: -0.0003

Data Index: 1107156 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3947. Min Act: -0.0003

Data Index: 816087 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4130. Min Act: -0.0003

Data Index: 338700 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.4318. Min Act: -0.0002

Data Index: 40200 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3769. Min Act: -0.0002

Data Index: 1153582 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3731. Min Act: -0.0003

Data Index: 676504 (C4 (Web Text))

Max Activating Token Index: 581