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

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

Neuron 5443 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6066. Min Act: -0.0000

Data Index: 105681 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6870. Min Act: -0.0000

Data Index: 264081 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6565. Min Act: -0.0000

Data Index: 50239 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.6346. Min Act: -0.0000

Data Index: 350309 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5933. Min Act: -0.0000

Data Index: 930782 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1055299 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5860. Min Act: -0.0000

Data Index: 702624 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5786. Min Act: -0.0000

Data Index: 606205 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5436. Min Act: -0.0000

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5386. Min Act: -0.0000

Data Index: 431783 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5506. Min Act: -0.0000

Data Index: 575952 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5451. Min Act: -0.0000

Data Index: 365983 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1162720 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1322690 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1123008 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5347. Min Act: -0.0000

Data Index: 40855 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4976. Min Act: -0.0000

Data Index: 138910 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.5032. Min Act: -0.0000

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1255611 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.6870. Min Range: -0.6870

Max Act: 0.4819. Min Act: -0.0000

Data Index: 215525 (C4 (Web Text))

Max Activating Token Index: 506