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

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

Neuron 3334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: -0.0001

Data Index: 1468955 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1360245 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4641. Min Act: -0.0000

Data Index: 54316 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1535077 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1478674 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4360. Min Act: -0.0001

Data Index: 1481847 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1511283 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1558167 (Python Code)

Max Activating Token Index: 579

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3708. Min Act: 0.0001

Data Index: 1446116 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1553911 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3583. Min Act: -0.0001

Data Index: 1471334 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1435424 (Python Code)

Max Activating Token Index: 360

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3684. Min Act: 0.0000

Data Index: 839145 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1594784 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1422899 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1461112 (Python Code)

Max Activating Token Index: 314

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1385470 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1150591 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1607064 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3240. Min Act: 0.0000

Data Index: 1526733 (Python Code)

Max Activating Token Index: 55