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

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

Neuron 628 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: 1.0963. Min Range: -1.0963

Max Act: 1.0963. Min Act: -0.0002

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9988. Min Act: -0.0002

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.0963. Min Range: -1.0963

Max Act: 1.0086. Min Act: -0.0002

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9705. Min Act: -0.0002

Data Index: 170651 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9795. Min Act: -0.0002

Data Index: 1118307 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9512. Min Act: -0.0002

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9405. Min Act: -0.0002

Data Index: 62693 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9274. Min Act: -0.0002

Data Index: 752485 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.9162. Min Act: -0.0002

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8852. Min Act: -0.0002

Data Index: 186214 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8736. Min Act: -0.0002

Data Index: 50225 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8551. Min Act: -0.0002

Data Index: 869038 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8301. Min Act: -0.0002

Data Index: 1256287 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8467. Min Act: -0.0002

Data Index: 53409 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8383. Min Act: -0.0002

Data Index: 1258070 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8148. Min Act: -0.0002

Data Index: 681635 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8325. Min Act: -0.0002

Data Index: 1266722 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8139. Min Act: -0.0002

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8204. Min Act: -0.0002

Data Index: 1193408 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.0963. Min Range: -1.0963

Max Act: 0.8098. Min Act: -0.0002

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 664