Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3624 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.8735. Min Act: -0.0001

Data Index: 1326070 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.7376. Min Act: -0.0001

Data Index: 1089350 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.8912. Min Act: -0.0001

Data Index: 1070810 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.5732. Min Act: -0.0001

Data Index: 235098 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.7377. Min Act: -0.0001

Data Index: 1296198 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.7340. Min Act: -0.0001

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6755. Min Act: -0.0001

Data Index: 364691 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6868. Min Act: -0.0001

Data Index: 385883 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.4921. Min Act: -0.0001

Data Index: 912811 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6638. Min Act: -0.0001

Data Index: 181495 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.5687. Min Act: -0.0001

Data Index: 566566 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6168. Min Act: -0.0001

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6081. Min Act: -0.0001

Data Index: 75011 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6445. Min Act: -0.0001

Data Index: 316344 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.5736. Min Act: -0.0001

Data Index: 1271728 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.6567. Min Act: -0.0001

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.5684. Min Act: -0.0001

Data Index: 1259670 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.5388. Min Act: -0.0001

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.4409. Min Act: -0.0001

Data Index: 70267 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 1.8912. Min Range: -1.8912

Max Act: 1.4641. Min Act: -0.0001

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 739