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

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

Neuron 594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1233999 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5503. Min Act: -0.0000

Data Index: 718113 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4611. Min Act: -0.0000

Data Index: 115447 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1272375 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5344. Min Act: -0.0000

Data Index: 643943 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4085. Min Act: -0.0000

Data Index: 631478 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3187. Min Act: -0.0000

Data Index: 820720 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2639. Min Act: -0.0000

Data Index: 844028 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1108742 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3129. Min Act: -0.0000

Data Index: 549975 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3035. Min Act: -0.0000

Data Index: 728879 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3131. Min Act: -0.0000

Data Index: 764998 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2664. Min Act: -0.0000

Data Index: 884060 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1267702 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1611907 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2888. Min Act: -0.0000

Data Index: 155521 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2642. Min Act: -0.0000

Data Index: 21033 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2617. Min Act: -0.0000

Data Index: 908475 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1318926 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1132465 (C4 (Web Text))

Max Activating Token Index: 560