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

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

Neuron 1075 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0001

Data Index: 382825 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3755. Min Act: -0.0001

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1195725 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3024. Min Act: -0.0001

Data Index: 274236 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3088. Min Act: -0.0001

Data Index: 142255 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3059. Min Act: -0.0001

Data Index: 207005 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2932. Min Act: -0.0001

Data Index: 450112 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3062. Min Act: -0.0001

Data Index: 360459 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3347. Min Act: -0.0001

Data Index: 873190 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3404. Min Act: -0.0001

Data Index: 867328 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2836. Min Act: -0.0001

Data Index: 116005 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3057. Min Act: -0.0001

Data Index: 82233 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2784. Min Act: -0.0001

Data Index: 287082 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1116035 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2856. Min Act: -0.0001

Data Index: 244355 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3361. Min Act: -0.0001

Data Index: 278410 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3011. Min Act: -0.0001

Data Index: 396003 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2896. Min Act: -0.0001

Data Index: 893779 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2789. Min Act: -0.0001

Data Index: 419734 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2825. Min Act: -0.0001

Data Index: 1348526 (C4 (Web Text))

Max Activating Token Index: 977