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

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

Neuron 471 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8704. Min Act: -0.0001

Data Index: 599384 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8782. Min Act: -0.0001

Data Index: 1005235 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 3.1093. Min Range: -3.1093

Max Act: 3.1093. Min Act: -0.0001

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7986. Min Act: -0.0001

Data Index: 1131804 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.5961. Min Act: -0.0001

Data Index: 346683 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.1093. Min Range: -3.1093

Max Act: 3.0746. Min Act: -0.0001

Data Index: 1113132 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7154. Min Act: -0.0001

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.4154. Min Act: -0.0001

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.3467. Min Act: -0.0001

Data Index: 1262470 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.6797. Min Act: -0.0001

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.4630. Min Act: -0.0001

Data Index: 696641 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.5923. Min Act: -0.0001

Data Index: 1224041 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.3347. Min Act: -0.0001

Data Index: 436303 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.5649. Min Act: -0.0001

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.4973. Min Act: -0.0000

Data Index: 221623 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.6491. Min Act: -0.0001

Data Index: 820183 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.2510. Min Act: -0.0001

Data Index: 369963 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.4105. Min Act: -0.0001

Data Index: 1026816 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.3326. Min Act: -0.0001

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.3187. Min Act: -0.0001

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 31