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

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

Neuron 280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0003

Data Index: 78948 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0003

Data Index: 282304 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1211024 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0003

Data Index: 232260 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1163600 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0003

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0003

Data Index: 892350 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 893965 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 376894 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0003

Data Index: 20082 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0003

Data Index: 770565 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0003

Data Index: 545578 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0003

Data Index: 511656 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1402336 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0003

Data Index: 727870 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1544143 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0003

Data Index: 281624 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0003

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1012562 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0003

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 659