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

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

Neuron 1434 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.5746. Min Act: -0.0001

Data Index: 616933 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3799. Min Act: -0.0001

Data Index: 518336 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3661. Min Act: -0.0001

Data Index: 475720 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3612. Min Act: -0.0001

Data Index: 107836 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3465. Min Act: -0.0001

Data Index: 665369 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3196. Min Act: -0.0001

Data Index: 1322355 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1234098 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3181. Min Act: -0.0001

Data Index: 980312 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3141. Min Act: -0.0001

Data Index: 352906 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3377. Min Act: -0.0001

Data Index: 1145709 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3241. Min Act: -0.0001

Data Index: 100451 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3182. Min Act: -0.0001

Data Index: 1063843 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3192. Min Act: -0.0001

Data Index: 599446 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3250. Min Act: -0.0001

Data Index: 652981 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1307925 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3095. Min Act: -0.0001

Data Index: 1291169 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3134. Min Act: -0.0001

Data Index: 238835 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3050. Min Act: -0.0001

Data Index: 747102 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1201363 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.5746. Min Range: -0.5746

Max Act: 0.3121. Min Act: -0.0001

Data Index: 660934 (C4 (Web Text))

Max Activating Token Index: 610