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

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

Neuron 4015 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1019902 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8576. Min Act: -0.0000

Data Index: 95525 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8260. Min Act: -0.0000

Data Index: 425787 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8512. Min Act: -0.0000

Data Index: 28368 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1037484 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8017. Min Act: -0.0000

Data Index: 733250 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8039. Min Act: -0.0000

Data Index: 517657 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7907. Min Act: -0.0000

Data Index: 753315 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7101. Min Act: -0.0000

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7580. Min Act: -0.0000

Data Index: 934684 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1205055 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1209005 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7079. Min Act: -0.0000

Data Index: 327447 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7172. Min Act: -0.0000

Data Index: 666003 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7123. Min Act: -0.0000

Data Index: 825095 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.6862. Min Act: -0.0000

Data Index: 20532 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.6863. Min Act: -0.0000

Data Index: 244822 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.6862. Min Act: -0.0000

Data Index: 26323 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.7461. Min Act: -0.0000

Data Index: 483309 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.6601. Min Act: -0.0000

Data Index: 128520 (C4 (Web Text))

Max Activating Token Index: 954