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

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

Neuron 2164 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: 1.9688. Min Range: -1.9688

Max Act: 1.9688. Min Act: -0.0001

Data Index: 377575 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.6067. Min Act: -0.0001

Data Index: 347192 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.3199. Min Act: -0.0001

Data Index: 794286 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.5053. Min Act: -0.0001

Data Index: 481873 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4319. Min Act: -0.0001

Data Index: 1128091 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.6298. Min Act: -0.0001

Data Index: 857368 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4736. Min Act: -0.0001

Data Index: 748365 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.8680. Min Act: -0.0001

Data Index: 841840 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4527. Min Act: -0.0001

Data Index: 853578 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.1036. Min Act: -0.0001

Data Index: 1286724 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.1301. Min Act: -0.0001

Data Index: 1050460 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.1741. Min Act: -0.0001

Data Index: 1276732 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.3236. Min Act: -0.0001

Data Index: 267049 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.3170. Min Act: -0.0001

Data Index: 314632 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4388. Min Act: -0.0001

Data Index: 1143325 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.5081. Min Act: -0.0001

Data Index: 524756 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.3376. Min Act: -0.0001

Data Index: 784669 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4119. Min Act: -0.0001

Data Index: 195835 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.3607. Min Act: -0.0001

Data Index: 1268399 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.9688. Min Range: -1.9688

Max Act: 1.4810. Min Act: -0.0001

Data Index: 192192 (C4 (Web Text))

Max Activating Token Index: 133