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

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

Neuron 3752 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: 0.4337. Min Range: -0.4337

Max Act: 0.4337. Min Act: -0.0001

Data Index: 1254634 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1115192 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3163. Min Act: -0.0000

Data Index: 596622 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3066. Min Act: -0.0000

Data Index: 247118 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1343328 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2650. Min Act: -0.0000

Data Index: 854099 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2527. Min Act: -0.0000

Data Index: 133481 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2506. Min Act: -0.0000

Data Index: 46337 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2654. Min Act: -0.0000

Data Index: 847840 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1172670 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2339. Min Act: -0.0000

Data Index: 456707 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2560. Min Act: -0.0001

Data Index: 598822 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1145668 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2418. Min Act: -0.0000

Data Index: 632303 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2124. Min Act: -0.0000

Data Index: 623449 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2149. Min Act: -0.0000

Data Index: 820419 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2148. Min Act: -0.0001

Data Index: 116327 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1046734 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1242083 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2089. Min Act: -0.0000

Data Index: 693471 (C4 (Web Text))

Max Activating Token Index: 359