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

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

Neuron 5675 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.2808. Min Act: -0.0003

Data Index: 310242 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.2057. Min Act: -0.0002

Data Index: 488055 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0579. Min Act: -0.0003

Data Index: 305565 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0427. Min Act: -0.0002

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0437. Min Act: -0.0003

Data Index: 1117881 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0201. Min Act: -0.0002

Data Index: 709758 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0165. Min Act: -0.0003

Data Index: 21043 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0089. Min Act: -0.0002

Data Index: 1235235 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9970. Min Act: -0.0002

Data Index: 866341 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9613. Min Act: -0.0002

Data Index: 291593 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9610. Min Act: -0.0002

Data Index: 1268579 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9624. Min Act: -0.0003

Data Index: 96865 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9567. Min Act: -0.0003

Data Index: 271105 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9610. Min Act: -0.0002

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9461. Min Act: -0.0003

Data Index: 584278 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9334. Min Act: -0.0003

Data Index: 986426 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9486. Min Act: -0.0002

Data Index: 79871 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9329. Min Act: -0.0003

Data Index: 16247 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9329. Min Act: -0.0002

Data Index: 509444 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9272. Min Act: -0.0002

Data Index: 1141432 (C4 (Web Text))

Max Activating Token Index: 296