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

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

Neuron 1566 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: 3.0714. Min Range: -3.0714

Max Act: 3.0714. Min Act: -0.0001

Data Index: 438879 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.0714. Min Range: -3.0714

Max Act: 3.0224. Min Act: -0.0000

Data Index: 30873 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.0714. Min Range: -3.0714

Max Act: 3.0675. Min Act: -0.0001

Data Index: 1248056 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3907. Min Act: -0.0001

Data Index: 36791 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.4998. Min Act: -0.0001

Data Index: 212823 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.7248. Min Act: -0.0001

Data Index: 711154 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3257. Min Act: -0.0001

Data Index: 703184 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.5630. Min Act: -0.0001

Data Index: 1237118 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.5068. Min Act: -0.0001

Data Index: 1271117 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3327. Min Act: -0.0001

Data Index: 1351454 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3313. Min Act: -0.0000

Data Index: 600095 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3780. Min Act: -0.0001

Data Index: 1321463 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.4866. Min Act: -0.0001

Data Index: 1227617 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.2469. Min Act: -0.0001

Data Index: 982084 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.1254. Min Act: -0.0001

Data Index: 1344053 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.2435. Min Act: -0.0001

Data Index: 1100510 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.3370. Min Act: -0.0001

Data Index: 1286937 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.4309. Min Act: -0.0001

Data Index: 1327954 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.1437. Min Act: -0.0001

Data Index: 749745 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.0714. Min Range: -3.0714

Max Act: 2.2418. Min Act: -0.0001

Data Index: 300317 (C4 (Web Text))

Max Activating Token Index: 349