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

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

Neuron 2757 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: 1.3956. Min Range: -1.3956

Max Act: 1.3956. Min Act: -0.0001

Data Index: 1031505 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.1593. Min Act: -0.0001

Data Index: 789196 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0992. Min Act: -0.0001

Data Index: 1194400 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9554. Min Act: -0.0001

Data Index: 686118 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0490. Min Act: -0.0001

Data Index: 526048 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0257. Min Act: -0.0001

Data Index: 652648 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0158. Min Act: -0.0001

Data Index: 462409 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0551. Min Act: -0.0001

Data Index: 1124337 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9031. Min Act: -0.0001

Data Index: 102302 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1100285 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9781. Min Act: -0.0001

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9361. Min Act: -0.0001

Data Index: 123305 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9716. Min Act: -0.0001

Data Index: 662256 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9266. Min Act: -0.0001

Data Index: 625837 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.8925. Min Act: -0.0001

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9027. Min Act: -0.0001

Data Index: 130395 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9420. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9083. Min Act: -0.0001

Data Index: 295726 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9079. Min Act: -0.0001

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1023615 (C4 (Web Text))

Max Activating Token Index: 706