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

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

Neuron 2132 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: 1.8201. Min Range: -1.8201

Max Act: 1.7379. Min Act: -0.0001

Data Index: 902999 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.8201. Min Act: -0.0001

Data Index: 263800 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.7271. Min Act: -0.0001

Data Index: 1537417 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.5826. Min Act: -0.0001

Data Index: 1447534 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.5066. Min Act: -0.0001

Data Index: 426832 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.5950. Min Act: -0.0001

Data Index: 1651951 (Python Code)

Max Activating Token Index: 633

Text #6

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.4063. Min Act: -0.0001

Data Index: 414041 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1540261 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.4002. Min Act: -0.0001

Data Index: 1603585 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1492875 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1483102 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.4852. Min Act: -0.0001

Data Index: 1523426 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3924. Min Act: -0.0001

Data Index: 1616943 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3359. Min Act: -0.0001

Data Index: 1429638 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3173. Min Act: -0.0001

Data Index: 143476 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3537. Min Act: -0.0001

Data Index: 1646646 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3493. Min Act: -0.0001

Data Index: 1301411 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3238. Min Act: -0.0001

Data Index: 1645726 (Python Code)

Max Activating Token Index: 803

Text #18

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1536459 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 1.8201. Min Range: -1.8201

Max Act: 1.2949. Min Act: -0.0001

Data Index: 68048 (C4 (Web Text))

Max Activating Token Index: 42