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

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

Neuron 3119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.3181. Min Act: -0.0000

Data Index: 1018441 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.3114. Min Act: -0.0000

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.0340. Min Act: -0.0000

Data Index: 627748 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.0326. Min Act: -0.0000

Data Index: 38104 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.1495. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.9962. Min Act: -0.0000

Data Index: 1134919 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1101983 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.8351. Min Act: -0.0000

Data Index: 64410 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 2.3181. Min Range: -2.3181

Max Act: 2.2681. Min Act: -0.0000

Data Index: 822604 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.7043. Min Act: -0.0000

Data Index: 14199 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.8094. Min Act: -0.0000

Data Index: 810457 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.8366. Min Act: -0.0000

Data Index: 672891 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.7495. Min Act: -0.0000

Data Index: 539858 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.9110. Min Act: -0.0000

Data Index: 233805 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1328009 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1196544 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.5461. Min Act: -0.0000

Data Index: 423698 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.7341. Min Act: -0.0000

Data Index: 137296 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.6425. Min Act: -0.0000

Data Index: 121790 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.3181. Min Range: -2.3181

Max Act: 1.8152. Min Act: -0.0000

Data Index: 910303 (C4 (Web Text))

Max Activating Token Index: 379