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

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

Neuron 466 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: 1.7078. Min Range: -1.7078

Max Act: 1.7078. Min Act: -0.0003

Data Index: 802191 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3781. Min Act: -0.0003

Data Index: 1036062 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3433. Min Act: -0.0003

Data Index: 1255509 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.2281. Min Act: -0.0003

Data Index: 223074 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1924. Min Act: -0.0003

Data Index: 812037 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.0500. Min Act: -0.0003

Data Index: 356109 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1353. Min Act: -0.0003

Data Index: 1214689 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.0585. Min Act: -0.0003

Data Index: 10945 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.0334. Min Act: -0.0003

Data Index: 383703 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9893. Min Act: -0.0003

Data Index: 639741 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.1362. Min Act: -0.0003

Data Index: 218143 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9812. Min Act: -0.0003

Data Index: 776297 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.0994. Min Act: -0.0003

Data Index: 605538 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9588. Min Act: -0.0003

Data Index: 1201482 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9898. Min Act: -0.0003

Data Index: 1174949 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9822. Min Act: -0.0003

Data Index: 995066 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.8671. Min Act: -0.0003

Data Index: 67013 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9557. Min Act: -0.0003

Data Index: 486807 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9733. Min Act: -0.0003

Data Index: 960758 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.7078. Min Range: -1.7078

Max Act: 0.9284. Min Act: -0.0003

Data Index: 1269984 (C4 (Web Text))

Max Activating Token Index: 278