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

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

Neuron 2200 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: 5.2748. Min Range: -5.2748

Max Act: 5.2748. Min Act: -0.0000

Data Index: 1009946 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.7357. Min Act: -0.0000

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.7363. Min Act: -0.0000

Data Index: 215762 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.7493. Min Act: -0.0000

Data Index: 702877 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.3862. Min Act: -0.0000

Data Index: 1133455 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.3111. Min Act: -0.0000

Data Index: 1215606 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.2048. Min Act: -0.0000

Data Index: 137165 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.0078. Min Act: -0.0000

Data Index: 264899 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 5.2748. Min Range: -5.2748

Max Act: 3.1244. Min Act: -0.0000

Data Index: 741061 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.9626. Min Act: -0.0000

Data Index: 797785 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.9935. Min Act: -0.0000

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.8243. Min Act: -0.0000

Data Index: 1343838 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1228921 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.7845. Min Act: -0.0000

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.9154. Min Act: -0.0000

Data Index: 1168062 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.7669. Min Act: -0.0000

Data Index: 891330 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.7365. Min Act: -0.0000

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.8175. Min Act: -0.0000

Data Index: 562119 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.6294. Min Act: -0.0000

Data Index: 215676 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 5.2748. Min Range: -5.2748

Max Act: 2.7644. Min Act: -0.0000

Data Index: 697127 (C4 (Web Text))

Max Activating Token Index: 366