Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2076 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8735. Min Range: -3.8735

Max Act: 3.8735. Min Act: -0.0000

Data Index: 1378685 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.6790. Min Act: -0.0000

Data Index: 1542655 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.6448. Min Act: -0.0000

Data Index: 1529575 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1569827 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.4912. Min Act: -0.0000

Data Index: 1436830 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.7774. Min Act: -0.0000

Data Index: 1456240 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.4809. Min Act: -0.0000

Data Index: 1593376 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.4649. Min Act: -0.0000

Data Index: 1581524 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1380388 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3844. Min Act: -0.0000

Data Index: 1644136 (Python Code)

Max Activating Token Index: 875

Text #10

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3745. Min Act: -0.0000

Data Index: 289799 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1130808 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3079. Min Act: -0.0000

Data Index: 1552004 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3969. Min Act: -0.0000

Data Index: 1623150 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.2698. Min Act: -0.0000

Data Index: 1458860 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.0607. Min Act: -0.0000

Data Index: 1521263 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.1145. Min Act: -0.0000

Data Index: 1517348 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 3.8735. Min Range: -3.8735

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1393257 (Python Code)

Max Activating Token Index: 998

Text #18

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.2114. Min Act: -0.0000

Data Index: 1482607 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 3.8735. Min Range: -3.8735

Max Act: 2.3222. Min Act: -0.0000

Data Index: 1419378 (Python Code)

Max Activating Token Index: 867