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

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

Neuron 2370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.4324. Min Act: -0.0002

Data Index: 482613 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.2800. Min Act: -0.0002

Data Index: 1267652 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.3480. Min Act: -0.0002

Data Index: 1201742 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1871. Min Act: -0.0002

Data Index: 1075829 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1510. Min Act: -0.0002

Data Index: 415522 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.2643. Min Act: -0.0002

Data Index: 539748 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1556. Min Act: -0.0002

Data Index: 430682 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1409. Min Act: -0.0002

Data Index: 1018681 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1499. Min Act: -0.0002

Data Index: 464236 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0797. Min Act: -0.0002

Data Index: 1081 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0698. Min Act: -0.0002

Data Index: 1266244 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1071. Min Act: -0.0002

Data Index: 982382 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0465. Min Act: -0.0002

Data Index: 632627 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0907. Min Act: -0.0002

Data Index: 514647 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9787. Min Act: -0.0002

Data Index: 356684 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0200. Min Act: -0.0002

Data Index: 626300 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0190. Min Act: -0.0002

Data Index: 1043258 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0205. Min Act: -0.0002

Data Index: 936394 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0101. Min Act: -0.0002

Data Index: 521840 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9909. Min Act: -0.0002

Data Index: 145604 (C4 (Web Text))

Max Activating Token Index: 734