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

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

Neuron 5130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.0659. Min Act: -0.0000

Data Index: 97580 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.1998. Min Act: -0.0000

Data Index: 936263 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8323. Min Act: -0.0000

Data Index: 538529 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.1810. Min Act: -0.0000

Data Index: 1284766 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8169. Min Act: -0.0000

Data Index: 435578 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.0036. Min Act: -0.0000

Data Index: 1094023 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.1494. Min Act: -0.0000

Data Index: 522957 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.9175. Min Act: -0.0000

Data Index: 947662 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8971. Min Act: -0.0000

Data Index: 646427 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8769. Min Act: -0.0000

Data Index: 835407 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8533. Min Act: -0.0000

Data Index: 992335 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.5363. Min Act: -0.0000

Data Index: 343732 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 4.2093. Min Range: -4.2093

Max Act: 4.2093. Min Act: -0.0000

Data Index: 337734 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.8104. Min Act: -0.0000

Data Index: 1172011 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.9725. Min Act: -0.0000

Data Index: 1219941 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.6454. Min Act: -0.0000

Data Index: 952011 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.9727. Min Act: -0.0000

Data Index: 793165 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.7854. Min Act: -0.0000

Data Index: 389886 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.7654. Min Act: -0.0000

Data Index: 1216088 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 4.2093. Min Range: -4.2093

Max Act: 3.7579. Min Act: -0.0000

Data Index: 11215 (C4 (Web Text))

Max Activating Token Index: 750