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

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

Neuron 692 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.4066. Min Act: -0.0000

Data Index: 432975 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1381044 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3433. Min Act: 0.0000

Data Index: 1578641 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3337. Min Act: 0.0000

Data Index: 1570886 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3387. Min Act: 0.0000

Data Index: 1418320 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1594605 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2963. Min Act: -0.0000

Data Index: 644785 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3163. Min Act: -0.0000

Data Index: 814072 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1223342 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2988. Min Act: -0.0000

Data Index: 228834 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2917. Min Act: -0.0000

Data Index: 604003 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2749. Min Act: -0.0000

Data Index: 883620 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1089817 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2875. Min Act: -0.0000

Data Index: 465552 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1474886 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2757. Min Act: -0.0000

Data Index: 99256 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2528. Min Act: -0.0000

Data Index: 684515 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1096931 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1351221 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2611. Min Act: -0.0000

Data Index: 741617 (C4 (Web Text))

Max Activating Token Index: 522