Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9566. Min Act: -0.0000

Data Index: 447786 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9288. Min Act: -0.0000

Data Index: 481685 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9713. Min Act: -0.0001

Data Index: 541892 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9142. Min Act: -0.0001

Data Index: 496706 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8776. Min Act: -0.0001

Data Index: 1114346 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9423. Min Act: -0.0001

Data Index: 1037900 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8763. Min Act: -0.0001

Data Index: 49438 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8643. Min Act: -0.0000

Data Index: 352573 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8517. Min Act: -0.0001

Data Index: 576218 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8521. Min Act: -0.0001

Data Index: 119067 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8492. Min Act: -0.0001

Data Index: 172240 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8292. Min Act: -0.0000

Data Index: 825806 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.7818. Min Act: -0.0001

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.7549. Min Act: -0.0001

Data Index: 586837 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1224090 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8091. Min Act: -0.0000

Data Index: 308066 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.7865. Min Act: -0.0001

Data Index: 708545 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8140. Min Act: -0.0001

Data Index: 124934 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1092867 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.8073. Min Act: -0.0001

Data Index: 503151 (C4 (Web Text))

Max Activating Token Index: 482