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

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

Neuron 4397 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: 0.4124. Min Range: -0.4124

Max Act: 0.4124. Min Act: 0.0000

Data Index: 744133 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3583. Min Act: -0.0000

Data Index: 827004 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1176669 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3641. Min Act: -0.0000

Data Index: 291075 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3844. Min Act: -0.0000

Data Index: 229876 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3589. Min Act: -0.0000

Data Index: 892357 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3538. Min Act: -0.0000

Data Index: 700687 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3394. Min Act: -0.0000

Data Index: 299158 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3263. Min Act: -0.0000

Data Index: 235119 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3328. Min Act: -0.0000

Data Index: 191563 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3240. Min Act: -0.0000

Data Index: 181026 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3038. Min Act: 0.0000

Data Index: 371050 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3114. Min Act: -0.0000

Data Index: 721376 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3012. Min Act: -0.0000

Data Index: 974348 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1187622 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2934. Min Act: -0.0000

Data Index: 271901 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2941. Min Act: -0.0000

Data Index: 848651 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2939. Min Act: -0.0000

Data Index: 234216 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2990. Min Act: 0.0000

Data Index: 1226072 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.2993. Min Act: -0.0000

Data Index: 884468 (C4 (Web Text))

Max Activating Token Index: 446