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

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

Neuron 3144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.8821. Min Act: -0.0001

Data Index: 529143 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.6986. Min Act: -0.0001

Data Index: 1026164 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5768. Min Act: -0.0001

Data Index: 1127416 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.8192. Min Act: -0.0001

Data Index: 1268402 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5552. Min Act: -0.0001

Data Index: 541738 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5410. Min Act: -0.0001

Data Index: 1217574 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1347758 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5530. Min Act: -0.0001

Data Index: 627261 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.6029. Min Act: -0.0001

Data Index: 349314 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4039. Min Act: -0.0001

Data Index: 49583 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4748. Min Act: -0.0001

Data Index: 895641 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5150. Min Act: -0.0001

Data Index: 71954 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4667. Min Act: -0.0001

Data Index: 988536 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.5332. Min Act: -0.0001

Data Index: 441749 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.3949. Min Act: -0.0001

Data Index: 1330527 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.3537. Min Act: -0.0001

Data Index: 244072 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.6375. Min Act: -0.0001

Data Index: 816650 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.3936. Min Act: -0.0001

Data Index: 774604 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.4905. Min Act: -0.0001

Data Index: 479622 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.8821. Min Range: -1.8821

Max Act: 1.2234. Min Act: -0.0001

Data Index: 1261278 (C4 (Web Text))

Max Activating Token Index: 850