Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2351 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0003

Data Index: 173591 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0003

Data Index: 741734 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1011621 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0004

Data Index: 795430 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0003

Data Index: 484425 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0003

Data Index: 964839 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0047. Min Act: -0.0003

Data Index: 761120 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0003

Data Index: 351449 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 56249 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 224307 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 163738 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 271066 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0041. Min Act: -0.0003

Data Index: 718208 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0040. Min Act: -0.0003

Data Index: 35889 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0040. Min Act: -0.0003

Data Index: 192400 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1464420 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1045112 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0039. Min Act: -0.0003

Data Index: 974716 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1646121 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0039. Min Act: -0.0003

Data Index: 945803 (C4 (Web Text))

Max Activating Token Index: 977