Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2900 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.8388. Min Act: -0.0001

Data Index: 828787 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.8286. Min Act: -0.0001

Data Index: 672375 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7737. Min Act: -0.0001

Data Index: 338188 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7980. Min Act: -0.0001

Data Index: 1073048 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7561. Min Act: -0.0001

Data Index: 683545 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.8600. Min Act: -0.0001

Data Index: 853346 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1202750 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7594. Min Act: -0.0001

Data Index: 152601 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6920. Min Act: -0.0001

Data Index: 350453 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7443. Min Act: -0.0001

Data Index: 154358 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7531. Min Act: -0.0001

Data Index: 242908 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6778. Min Act: -0.0001

Data Index: 836184 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1040921 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1230460 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7123. Min Act: -0.0001

Data Index: 492885 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6914. Min Act: -0.0001

Data Index: 1119394 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7563. Min Act: -0.0001

Data Index: 119971 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6743. Min Act: -0.0001

Data Index: 592867 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1033005 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7005. Min Act: -0.0001

Data Index: 150396 (C4 (Web Text))

Max Activating Token Index: 575