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

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

Neuron 4557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1069597 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.2085. Min Act: -0.0000

Data Index: 591151 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.1758. Min Act: -0.0000

Data Index: 793567 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0569. Min Act: -0.0000

Data Index: 853064 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1094423 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0808. Min Act: -0.0000

Data Index: 204479 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1122150 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0199. Min Act: -0.0000

Data Index: 366046 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9643. Min Act: -0.0000

Data Index: 573638 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1232021 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.2787. Min Range: -1.2787

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1040490 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1282526 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1064327 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9316. Min Act: -0.0000

Data Index: 623085 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9531. Min Act: -0.0000

Data Index: 333255 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1082622 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9706. Min Act: -0.0000

Data Index: 817170 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9320. Min Act: -0.0000

Data Index: 557535 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.9205. Min Act: -0.0000

Data Index: 759104 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.2787. Min Range: -1.2787

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1049130 (C4 (Web Text))

Max Activating Token Index: 912