Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.2494. Min Act: -0.0003

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.1349. Min Act: -0.0003

Data Index: 1248693 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.1340. Min Act: -0.0003

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0488. Min Act: -0.0003

Data Index: 1466375 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0622. Min Act: -0.0003

Data Index: 708244 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.2494. Min Range: -1.2494

Max Act: 1.0146. Min Act: -0.0003

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9676. Min Act: -0.0003

Data Index: 156696 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9980. Min Act: -0.0003

Data Index: 467119 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9360. Min Act: -0.0003

Data Index: 1120382 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9774. Min Act: -0.0003

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9428. Min Act: -0.0003

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9550. Min Act: -0.0003

Data Index: 1545039 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8732. Min Act: -0.0003

Data Index: 1403831 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8887. Min Act: -0.0003

Data Index: 1304746 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8825. Min Act: -0.0003

Data Index: 1169244 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.9171. Min Act: -0.0003

Data Index: 96040 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8871. Min Act: -0.0003

Data Index: 1240920 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.8184. Min Act: -0.0003

Data Index: 1299617 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.7994. Min Act: -0.0003

Data Index: 925561 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.2494. Min Range: -1.2494

Max Act: 0.7655. Min Act: -0.0003

Data Index: 47431 (C4 (Web Text))

Max Activating Token Index: 591