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

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

Neuron 2905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1018956 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.4724. Min Act: -0.0000

Data Index: 562085 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1979. Min Act: -0.0000

Data Index: 952827 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.3095. Min Act: -0.0000

Data Index: 720647 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1961. Min Act: -0.0000

Data Index: 581028 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.2768. Min Act: -0.0000

Data Index: 897872 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1063. Min Act: -0.0000

Data Index: 957442 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0411. Min Act: -0.0000

Data Index: 115440 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1279038 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1191555 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1271152 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0759. Min Act: -0.0000

Data Index: 361508 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9678. Min Act: -0.0000

Data Index: 249199 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0936. Min Act: -0.0000

Data Index: 384614 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1090725 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9596. Min Act: -0.0000

Data Index: 440828 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9654. Min Act: -0.0000

Data Index: 250784 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1024834 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0083. Min Act: -0.0000

Data Index: 24229 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9472. Min Act: -0.0000

Data Index: 726468 (C4 (Web Text))

Max Activating Token Index: 318