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

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

Neuron 4154 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.4006. Min Act: -0.0001

Data Index: 20703 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1285771 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3553. Min Act: -0.0000

Data Index: 931783 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3241. Min Act: -0.0001

Data Index: 1303620 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3330. Min Act: -0.0000

Data Index: 46097 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3349. Min Act: -0.0000

Data Index: 853080 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3139. Min Act: -0.0000

Data Index: 836151 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3156. Min Act: -0.0000

Data Index: 516817 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3008. Min Act: -0.0000

Data Index: 32091 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1226864 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1133468 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3186. Min Act: -0.0001

Data Index: 640143 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.2948. Min Act: -0.0001

Data Index: 235068 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3159. Min Act: -0.0001

Data Index: 435792 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1070868 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1303947 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3196. Min Act: -0.0001

Data Index: 939368 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.3129. Min Act: -0.0000

Data Index: 993413 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.2968. Min Act: -0.0000

Data Index: 686142 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.4006. Min Range: -0.4006

Max Act: 0.2948. Min Act: -0.0001

Data Index: 386999 (C4 (Web Text))

Max Activating Token Index: 637