Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2241. Min Range: -2.2241

Max Act: 2.1050. Min Act: -0.0000

Data Index: 903910 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.8114. Min Act: -0.0000

Data Index: 16801 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1136056 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7143. Min Act: -0.0000

Data Index: 281100 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 2.2241. Min Range: -2.2241

Max Act: 2.2241. Min Act: -0.0000

Data Index: 304043 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5914. Min Act: -0.0000

Data Index: 186874 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.6640. Min Act: -0.0000

Data Index: 942536 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7236. Min Act: -0.0000

Data Index: 1103582 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7152. Min Act: -0.0000

Data Index: 1049371 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7079. Min Act: -0.0000

Data Index: 725641 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5904. Min Act: -0.0000

Data Index: 705357 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5775. Min Act: -0.0000

Data Index: 60841 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.6809. Min Act: -0.0000

Data Index: 937403 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.7610. Min Act: -0.0000

Data Index: 320939 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5689. Min Act: -0.0000

Data Index: 1037820 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5533. Min Act: -0.0000

Data Index: 796396 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1235691 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1066382 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.4796. Min Act: -0.0000

Data Index: 1171586 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 2.2241. Min Range: -2.2241

Max Act: 1.6327. Min Act: -0.0000

Data Index: 337312 (C4 (Web Text))

Max Activating Token Index: 226