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

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

Neuron 3364 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.9758. Min Range: -14.9758

Max Act: 14.9758. Min Act: -0.0000

Data Index: 430215 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 14.9758. Min Range: -14.9758

Max Act: 14.6299. Min Act: -0.0000

Data Index: 201120 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 14.9758. Min Range: -14.9758

Max Act: 13.7898. Min Act: -0.0000

Data Index: 1121270 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 14.9758. Min Range: -14.9758

Max Act: 13.6309. Min Act: -0.0000

Data Index: 451529 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 14.9758. Min Range: -14.9758

Max Act: 13.0649. Min Act: -0.0000

Data Index: 586906 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 14.9758. Min Range: -14.9758

Max Act: 12.8288. Min Act: -0.0000

Data Index: 1290251 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 14.9758. Min Range: -14.9758

Max Act: 13.1525. Min Act: -0.0000

Data Index: 168005 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 14.9758. Min Range: -14.9758

Max Act: 12.8899. Min Act: -0.0000

Data Index: 1121864 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 14.9758. Min Range: -14.9758

Max Act: 12.1711. Min Act: -0.0000

Data Index: 19640 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 14.9758. Min Range: -14.9758

Max Act: 12.1893. Min Act: -0.0000

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 14.9758. Min Range: -14.9758

Max Act: 12.3630. Min Act: -0.0000

Data Index: 490028 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 14.9758. Min Range: -14.9758

Max Act: 11.3991. Min Act: -0.0000

Data Index: 215469 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 14.9758. Min Range: -14.9758

Max Act: 10.9258. Min Act: -0.0000

Data Index: 132612 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 14.9758. Min Range: -14.9758

Max Act: 11.8852. Min Act: -0.0000

Data Index: 1221242 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 14.9758. Min Range: -14.9758

Max Act: 10.6554. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 14.9758. Min Range: -14.9758

Max Act: 11.2279. Min Act: -0.0000

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 14.9758. Min Range: -14.9758

Max Act: 11.1167. Min Act: -0.0000

Data Index: 563220 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 14.9758. Min Range: -14.9758

Max Act: 11.7760. Min Act: -0.0000

Data Index: 998911 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 14.9758. Min Range: -14.9758

Max Act: 10.0691. Min Act: -0.0000

Data Index: 206236 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 14.9758. Min Range: -14.9758

Max Act: 10.5243. Min Act: -0.0000

Data Index: 1175595 (C4 (Web Text))

Max Activating Token Index: 987