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

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

Neuron 3136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.4110. Min Act: -0.0000

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1580108 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1303743 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3146. Min Act: -0.0000

Data Index: 120559 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3132. Min Act: -0.0000

Data Index: 106638 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3241. Min Act: -0.0000

Data Index: 880656 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1163267 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1041031 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3095. Min Act: -0.0000

Data Index: 300823 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2962. Min Act: -0.0000

Data Index: 257050 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3172. Min Act: -0.0000

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3083. Min Act: -0.0000

Data Index: 457153 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3047. Min Act: -0.0000

Data Index: 564329 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3138. Min Act: -0.0000

Data Index: 439927 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3003. Min Act: -0.0000

Data Index: 428180 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2883. Min Act: -0.0000

Data Index: 491525 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3061. Min Act: -0.0000

Data Index: 691328 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1131873 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2943. Min Act: -0.0000

Data Index: 86760 (C4 (Web Text))

Max Activating Token Index: 282