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

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

Neuron 775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3153. Min Act: -0.0001

Data Index: 641665 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2879. Min Act: -0.0001

Data Index: 770238 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2736. Min Act: -0.0001

Data Index: 587631 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2623. Min Act: -0.0000

Data Index: 168145 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2550. Min Act: -0.0001

Data Index: 997358 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2614. Min Act: -0.0001

Data Index: 522618 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2469. Min Act: -0.0000

Data Index: 83492 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2687. Min Act: -0.0001

Data Index: 790381 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2467. Min Act: -0.0001

Data Index: 919909 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2365. Min Act: -0.0001

Data Index: 862425 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2583. Min Act: -0.0001

Data Index: 644800 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1050653 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1140326 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2238. Min Act: -0.0001

Data Index: 495232 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2590. Min Act: -0.0000

Data Index: 949674 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2091. Min Act: -0.0000

Data Index: 334537 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.1869. Min Act: -0.0000

Data Index: 25974 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2331. Min Act: -0.0001

Data Index: 503516 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2283. Min Act: -0.0001

Data Index: 133428 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1321312 (C4 (Web Text))

Max Activating Token Index: 424