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

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

Neuron 4815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0001

Data Index: 619458 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3440. Min Act: -0.0001

Data Index: 436821 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1192548 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1077261 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3058. Min Act: -0.0001

Data Index: 1120407 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3034. Min Act: -0.0001

Data Index: 391453 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3032. Min Act: -0.0001

Data Index: 604480 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3219. Min Act: -0.0001

Data Index: 19734 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3246. Min Act: -0.0001

Data Index: 224345 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2892. Min Act: -0.0001

Data Index: 377434 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1327962 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2906. Min Act: -0.0001

Data Index: 653864 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2911. Min Act: -0.0001

Data Index: 613433 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3222. Min Act: -0.0001

Data Index: 75051 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2970. Min Act: -0.0001

Data Index: 589129 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2759. Min Act: -0.0001

Data Index: 796784 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1322827 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1132780 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2802. Min Act: -0.0001

Data Index: 557650 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2681. Min Act: -0.0001

Data Index: 1220696 (C4 (Web Text))

Max Activating Token Index: 632