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

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

Neuron 2602 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3303. Min Range: -2.3303

Max Act: 2.3303. Min Act: -0.0000

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1101538 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.8702. Min Act: -0.0001

Data Index: 1193710 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.7693. Min Act: -0.0000

Data Index: 718433 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.8244. Min Act: -0.0000

Data Index: 589280 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.7575. Min Act: -0.0000

Data Index: 498213 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.9323. Min Act: -0.0001

Data Index: 516183 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6158. Min Act: -0.0000

Data Index: 477531 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6324. Min Act: -0.0001

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1275255 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.4180. Min Act: -0.0000

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6447. Min Act: -0.0000

Data Index: 624588 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1152118 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1236388 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1339117 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.5952. Min Act: -0.0000

Data Index: 318297 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.5100. Min Act: -0.0000

Data Index: 884403 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6285. Min Act: -0.0000

Data Index: 418160 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.6098. Min Act: -0.0001

Data Index: 970018 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 2.3303. Min Range: -2.3303

Max Act: 1.5912. Min Act: -0.0001

Data Index: 1100213 (C4 (Web Text))

Max Activating Token Index: 394