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

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

Neuron 1593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0000

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2963. Min Act: -0.0000

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3055. Min Act: -0.0000

Data Index: 2745 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2943. Min Act: -0.0000

Data Index: 221387 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2926. Min Act: -0.0000

Data Index: 248999 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1087513 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1124751 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2751. Min Act: -0.0000

Data Index: 761957 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2811. Min Act: 0.0000

Data Index: 785537 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2544. Min Act: -0.0000

Data Index: 333332 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1280742 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2663. Min Act: 0.0000

Data Index: 291721 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2601. Min Act: -0.0000

Data Index: 759380 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2493. Min Act: -0.0000

Data Index: 579042 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2441. Min Act: -0.0000

Data Index: 908551 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1332998 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2442. Min Act: -0.0000

Data Index: 437942 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2509. Min Act: -0.0000

Data Index: 358463 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2504. Min Act: -0.0000

Data Index: 356288 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2494. Min Act: -0.0000

Data Index: 437299 (C4 (Web Text))

Max Activating Token Index: 805