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

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

Neuron 2595 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1049625 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.7736. Min Act: -0.0000

Data Index: 803196 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.6263. Min Act: -0.0000

Data Index: 159867 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.8138. Min Act: -0.0000

Data Index: 1258119 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.5552. Min Act: -0.0000

Data Index: 57534 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.6082. Min Act: -0.0000

Data Index: 1274724 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1007807 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4607. Min Act: -0.0000

Data Index: 788438 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1032644 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4837. Min Act: -0.0000

Data Index: 515728 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1079987 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4030. Min Act: -0.0000

Data Index: 974314 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.3952. Min Act: -0.0000

Data Index: 316084 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1291716 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.2693. Min Act: -0.0000

Data Index: 382466 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.2793. Min Act: -0.0000

Data Index: 189426 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.4166. Min Act: -0.0000

Data Index: 933614 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.2575. Min Act: -0.0000

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1018821 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.9094. Min Range: -1.9094

Max Act: 1.3057. Min Act: -0.0000

Data Index: 488093 (C4 (Web Text))

Max Activating Token Index: 578