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

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

Neuron 4826 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5369. Min Range: -2.5369

Max Act: 2.5369. Min Act: -0.0000

Data Index: 558488 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 2.5369. Min Range: -2.5369

Max Act: 2.0067. Min Act: -0.0000

Data Index: 754799 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.7845. Min Act: -0.0000

Data Index: 801911 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5533. Min Act: -0.0000

Data Index: 118165 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5582. Min Act: -0.0000

Data Index: 858759 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5502. Min Act: -0.0000

Data Index: 458901 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5332. Min Act: -0.0000

Data Index: 1356747 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5043. Min Act: -0.0000

Data Index: 498300 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1280178 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1066550 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4855. Min Act: -0.0000

Data Index: 196383 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.5749. Min Act: -0.0000

Data Index: 47120 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4856. Min Act: -0.0000

Data Index: 100686 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4523. Min Act: -0.0000

Data Index: 812751 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4309. Min Act: -0.0000

Data Index: 86499 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.4302. Min Act: -0.0000

Data Index: 285101 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1187371 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.3937. Min Act: -0.0000

Data Index: 796069 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.3845. Min Act: -0.0000

Data Index: 606668 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 2.5369. Min Range: -2.5369

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1160092 (C4 (Web Text))

Max Activating Token Index: 811