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

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

Neuron 3901 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8695. Min Act: -0.0001

Data Index: 544382 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9110. Min Act: -0.0002

Data Index: 231554 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0002

Data Index: 547598 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9093. Min Act: -0.0001

Data Index: 279868 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8398. Min Act: -0.0001

Data Index: 1168582 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8435. Min Act: -0.0001

Data Index: 822798 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8355. Min Act: -0.0002

Data Index: 1194520 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8134. Min Act: -0.0002

Data Index: 340414 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8004. Min Act: -0.0002

Data Index: 971020 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1355257 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7766. Min Act: -0.0001

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7916. Min Act: -0.0002

Data Index: 1158797 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7397. Min Act: -0.0001

Data Index: 639115 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1239105 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7413. Min Act: -0.0001

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7722. Min Act: -0.0001

Data Index: 812459 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7565. Min Act: -0.0001

Data Index: 383327 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1335918 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7423. Min Act: -0.0001

Data Index: 1203283 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1020343 (C4 (Web Text))

Max Activating Token Index: 664