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

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

Neuron 815 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: 1.8367. Min Range: -1.8367

Max Act: 1.8367. Min Act: -0.0001

Data Index: 29591 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.5642. Min Act: -0.0001

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.4689. Min Act: -0.0001

Data Index: 993547 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3881. Min Act: -0.0001

Data Index: 813435 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3703. Min Act: -0.0001

Data Index: 831307 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1349855 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.2979. Min Act: -0.0001

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.3568. Min Act: -0.0001

Data Index: 456580 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.2930. Min Act: -0.0001

Data Index: 342463 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.2687. Min Act: -0.0001

Data Index: 819042 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.2083. Min Act: -0.0001

Data Index: 1007351 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.1250. Min Act: -0.0001

Data Index: 1014517 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.8367. Min Range: -1.8367

Max Act: 1.1124. Min Act: -0.0001

Data Index: 900226 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.9939. Min Act: -0.0001

Data Index: 1139419 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.9772. Min Act: -0.0001

Data Index: 154760 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.9602. Min Act: -0.0001

Data Index: 841597 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.8906. Min Act: -0.0001

Data Index: 1130180 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.8933. Min Act: -0.0001

Data Index: 1358754 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1254803 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.8367. Min Range: -1.8367

Max Act: 0.9631. Min Act: -0.0001

Data Index: 568320 (C4 (Web Text))

Max Activating Token Index: 866