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

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

Neuron 879 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: 10.0880. Min Range: -10.0880

Max Act: 10.0880. Min Act: -0.0001

Data Index: 635774 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.8518. Min Act: -0.0001

Data Index: 554115 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.5925. Min Act: -0.0001

Data Index: 1160396 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.3584. Min Act: -0.0001

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.4572. Min Act: -0.0001

Data Index: 1179377 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.2824. Min Act: -0.0001

Data Index: 1117104 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.1676. Min Act: -0.0001

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.0668. Min Act: -0.0001

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 10.0880. Min Range: -10.0880

Max Act: 9.1370. Min Act: -0.0001

Data Index: 740818 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.2678. Min Act: -0.0001

Data Index: 496328 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.5795. Min Act: -0.0001

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.7262. Min Act: -0.0001

Data Index: 368241 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.6237. Min Act: -0.0001

Data Index: 1011232 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.4398. Min Act: -0.0001

Data Index: 999000 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.7236. Min Act: -0.0001

Data Index: 711790 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.4154. Min Act: -0.0001

Data Index: 644878 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.3092. Min Act: -0.0001

Data Index: 360801 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.5157. Min Act: -0.0001

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.1848. Min Act: -0.0001

Data Index: 1293901 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 10.0880. Min Range: -10.0880

Max Act: 8.4619. Min Act: -0.0001

Data Index: 759449 (C4 (Web Text))

Max Activating Token Index: 112