Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5525 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1245200 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1021544 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2787. Min Act: -0.0000

Data Index: 988673 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2674. Min Act: 0.0000

Data Index: 761472 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2688. Min Act: 0.0000

Data Index: 34154 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1030226 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1022028 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2609. Min Act: 0.0000

Data Index: 80882 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2555. Min Act: 0.0000

Data Index: 1275556 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1120546 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2933. Min Act: -0.0000

Data Index: 150713 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2526. Min Act: -0.0000

Data Index: 502825 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1086671 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2455. Min Act: -0.0000

Data Index: 228797 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2543. Min Act: -0.0000

Data Index: 719003 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2446. Min Act: -0.0000

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1304644 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1212972 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2310. Min Act: -0.0000

Data Index: 250372 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.3095. Min Range: -0.3095

Max Act: 0.2225. Min Act: -0.0000

Data Index: 546148 (C4 (Web Text))

Max Activating Token Index: 208