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

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

Neuron 3303 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.8464. Min Act: -0.0000

Data Index: 157280 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.8203. Min Act: -0.0000

Data Index: 407532 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.7339. Min Act: -0.0000

Data Index: 181280 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.6043. Min Act: -0.0000

Data Index: 1265463 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.7135. Min Act: -0.0000

Data Index: 1306245 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5873. Min Act: -0.0000

Data Index: 797518 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.6135. Min Act: -0.0000

Data Index: 173323 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4490. Min Act: -0.0000

Data Index: 1064986 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5539. Min Act: -0.0000

Data Index: 1206939 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5815. Min Act: -0.0000

Data Index: 882118 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5194. Min Act: -0.0000

Data Index: 106531 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4955. Min Act: -0.0000

Data Index: 938307 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4772. Min Act: -0.0000

Data Index: 313874 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5634. Min Act: -0.0000

Data Index: 386784 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4362. Min Act: -0.0000

Data Index: 1047987 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4681. Min Act: -0.0000

Data Index: 859021 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.7045. Min Act: -0.0000

Data Index: 878824 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.3281. Min Act: -0.0000

Data Index: 1225213 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.5643. Min Act: -0.0000

Data Index: 1247006 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.8464. Min Range: -2.8464

Max Act: 2.4393. Min Act: -0.0000

Data Index: 434631 (C4 (Web Text))

Max Activating Token Index: 908