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

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

Neuron 2567 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: 4.4115. Min Range: -4.4115

Max Act: 4.4115. Min Act: -0.0000

Data Index: 619600 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 4.4115. Min Range: -4.4115

Max Act: 4.2330. Min Act: -0.0000

Data Index: 795032 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 4.4115. Min Range: -4.4115

Max Act: 4.3282. Min Act: -0.0000

Data Index: 1128163 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 4.4115. Min Range: -4.4115

Max Act: 4.0840. Min Act: -0.0000

Data Index: 505143 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 4.4115. Min Range: -4.4115

Max Act: 4.0792. Min Act: -0.0000

Data Index: 74285 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 4.4115. Min Range: -4.4115

Max Act: 4.0815. Min Act: -0.0000

Data Index: 32764 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.9212. Min Act: -0.0000

Data Index: 1251563 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.8036. Min Act: -0.0000

Data Index: 1040987 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.5788. Min Act: -0.0000

Data Index: 627090 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.6235. Min Act: -0.0000

Data Index: 862593 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.6372. Min Act: -0.0000

Data Index: 746667 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.6180. Min Act: -0.0000

Data Index: 28063 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.5853. Min Act: -0.0000

Data Index: 420950 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.5940. Min Act: -0.0000

Data Index: 1037435 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.7054. Min Act: -0.0000

Data Index: 53458 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.5409. Min Act: -0.0000

Data Index: 635311 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.5470. Min Act: -0.0000

Data Index: 119758 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.3430. Min Act: -0.0000

Data Index: 1276052 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.1980. Min Act: -0.0000

Data Index: 51986 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.4115. Min Range: -4.4115

Max Act: 3.3084. Min Act: -0.0000

Data Index: 186436 (C4 (Web Text))

Max Activating Token Index: 455