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

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

Neuron 19 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.3347. Min Act: -0.0000

Data Index: 549197 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0548. Min Act: -0.0000

Data Index: 90687 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.7373. Min Act: -0.0000

Data Index: 26293 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9204. Min Act: -0.0000

Data Index: 133211 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.5494. Min Act: -0.0000

Data Index: 1276 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9489. Min Act: -0.0000

Data Index: 554105 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.5022. Min Act: -0.0000

Data Index: 871510 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.7564. Min Act: -0.0000

Data Index: 294514 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.5926. Min Act: -0.0000

Data Index: 267355 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1537288 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.6750. Min Act: -0.0000

Data Index: 836803 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.6691. Min Act: -0.0000

Data Index: 196594 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.6147. Min Act: -0.0000

Data Index: 902379 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.6180. Min Act: -0.0000

Data Index: 1167342 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.4540. Min Act: -0.0000

Data Index: 1322288 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.5619. Min Act: -0.0000

Data Index: 1016350 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1254984 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.4274. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.4078. Min Act: -0.0000

Data Index: 986971 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.3633. Min Act: -0.0000

Data Index: 1233658 (C4 (Web Text))

Max Activating Token Index: 934