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

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

Neuron 755 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: 2.8520. Min Range: -2.8520

Max Act: 2.8520. Min Act: -0.0002

Data Index: 105117 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.7303. Min Act: -0.0002

Data Index: 993867 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5497. Min Act: -0.0002

Data Index: 999901 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5495. Min Act: -0.0002

Data Index: 1206287 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5480. Min Act: -0.0002

Data Index: 937962 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5165. Min Act: -0.0002

Data Index: 1188114 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5295. Min Act: -0.0002

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.5031. Min Act: -0.0003

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4841. Min Act: -0.0002

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4258. Min Act: -0.0002

Data Index: 448718 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4413. Min Act: -0.0002

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4483. Min Act: -0.0002

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4871. Min Act: -0.0002

Data Index: 764855 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4242. Min Act: -0.0002

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4853. Min Act: -0.0003

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4319. Min Act: -0.0002

Data Index: 885518 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.3969. Min Act: -0.0002

Data Index: 752303 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4909. Min Act: -0.0002

Data Index: 1235758 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.4209. Min Act: -0.0002

Data Index: 939261 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 2.8520. Min Range: -2.8520

Max Act: 2.3680. Min Act: -0.0002

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 928