Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2545 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.4090. Min Act: -0.0001

Data Index: 603960 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1246068 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3731. Min Act: -0.0001

Data Index: 809280 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3574. Min Act: -0.0001

Data Index: 125063 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3579. Min Act: -0.0001

Data Index: 973840 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3554. Min Act: -0.0001

Data Index: 898176 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3247. Min Act: -0.0001

Data Index: 166114 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3374. Min Act: -0.0001

Data Index: 193381 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3015. Min Act: -0.0001

Data Index: 426387 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3319. Min Act: -0.0001

Data Index: 901383 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1146486 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3301. Min Act: -0.0001

Data Index: 843237 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3182. Min Act: -0.0001

Data Index: 326609 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3171. Min Act: -0.0001

Data Index: 858812 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3148. Min Act: -0.0001

Data Index: 1016404 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3171. Min Act: -0.0001

Data Index: 1232056 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3246. Min Act: -0.0001

Data Index: 846179 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1063484 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3097. Min Act: -0.0001

Data Index: 465005 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1341870 (C4 (Web Text))

Max Activating Token Index: 631