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

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

Neuron 4463 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: 0.3431. Min Range: -0.3431

Max Act: 0.3246. Min Act: -0.0001

Data Index: 619940 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3431. Min Act: -0.0001

Data Index: 658237 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3123. Min Act: -0.0001

Data Index: 215206 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1008458 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3085. Min Act: -0.0001

Data Index: 1060858 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3148. Min Act: -0.0001

Data Index: 190818 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2893. Min Act: -0.0001

Data Index: 562500 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3006. Min Act: -0.0001

Data Index: 932088 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3047. Min Act: -0.0001

Data Index: 162891 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1191673 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2721. Min Act: -0.0001

Data Index: 142534 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3089. Min Act: -0.0001

Data Index: 275862 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2760. Min Act: -0.0001

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3094. Min Act: -0.0001

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2843. Min Act: -0.0001

Data Index: 886433 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3007. Min Act: -0.0000

Data Index: 178739 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.3016. Min Act: -0.0001

Data Index: 28494 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.3431. Min Range: -0.3431

Max Act: 0.2897. Min Act: -0.0001

Data Index: 149167 (C4 (Web Text))

Max Activating Token Index: 939