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

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

Neuron 385 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: 4.4712. Min Range: -4.4712

Max Act: 4.4712. Min Act: -0.0000

Data Index: 1066687 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 4.4712. Min Range: -4.4712

Max Act: 4.1397. Min Act: -0.0001

Data Index: 1223072 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.9212. Min Act: -0.0000

Data Index: 646381 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 4.4712. Min Range: -4.4712

Max Act: 4.0373. Min Act: -0.0000

Data Index: 425185 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.8429. Min Act: -0.0000

Data Index: 42765 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.9903. Min Act: -0.0000

Data Index: 958651 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.6384. Min Act: -0.0000

Data Index: 946983 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.5866. Min Act: -0.0000

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.7681. Min Act: -0.0000

Data Index: 1219463 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.8454. Min Act: -0.0000

Data Index: 1096711 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.6681. Min Act: -0.0000

Data Index: 74880 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.8144. Min Act: -0.0000

Data Index: 403161 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.3257. Min Act: -0.0001

Data Index: 1359345 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.4391. Min Act: -0.0001

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.5714. Min Act: -0.0000

Data Index: 937680 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.5212. Min Act: -0.0000

Data Index: 502379 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.5051. Min Act: -0.0001

Data Index: 32188 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.6496. Min Act: -0.0000

Data Index: 348954 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.6309. Min Act: -0.0000

Data Index: 908410 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 4.4712. Min Range: -4.4712

Max Act: 3.4529. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 489