Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3497. Min Act: -0.0001

Data Index: 780807 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3239. Min Act: -0.0001

Data Index: 569107 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1051053 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3295. Min Act: -0.0001

Data Index: 887237 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3160. Min Act: -0.0001

Data Index: 1187460 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3058. Min Act: -0.0001

Data Index: 1427555 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3065. Min Act: -0.0001

Data Index: 532834 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1261325 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1637401 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2968. Min Act: -0.0001

Data Index: 164317 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1461779 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1543856 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3016. Min Act: -0.0001

Data Index: 851437 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2907. Min Act: -0.0001

Data Index: 1475054 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1411839 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3122. Min Act: -0.0001

Data Index: 653908 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2975. Min Act: -0.0001

Data Index: 826651 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1443417 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2953. Min Act: -0.0001

Data Index: 1484144 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2861. Min Act: -0.0001

Data Index: 42309 (C4 (Web Text))

Max Activating Token Index: 562