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

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

Neuron 3932 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.4673. Min Act: -0.0002

Data Index: 1288539 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3352. Min Act: -0.0002

Data Index: 1002054 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2844. Min Act: -0.0002

Data Index: 985560 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1993. Min Act: -0.0002

Data Index: 670465 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1941. Min Act: -0.0002

Data Index: 1227809 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1887. Min Act: -0.0002

Data Index: 809340 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1418. Min Act: -0.0002

Data Index: 101793 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1559. Min Act: -0.0002

Data Index: 745601 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1330. Min Act: -0.0002

Data Index: 580526 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1342. Min Act: -0.0002

Data Index: 151134 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0817. Min Act: -0.0002

Data Index: 1303395 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1673. Min Act: -0.0002

Data Index: 246594 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1762. Min Act: -0.0002

Data Index: 432967 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1669. Min Act: -0.0002

Data Index: 89815 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0940. Min Act: -0.0002

Data Index: 286524 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1148. Min Act: -0.0002

Data Index: 994336 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1027. Min Act: -0.0002

Data Index: 478040 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1389. Min Act: -0.0002

Data Index: 799022 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0819. Min Act: -0.0002

Data Index: 1191271 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0983. Min Act: -0.0002

Data Index: 789158 (C4 (Web Text))

Max Activating Token Index: 870