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

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

Neuron 725 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0001

Data Index: 448245 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1067709 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1230998 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7154. Min Act: -0.0001

Data Index: 1546489 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1107647 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1040545 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1415490 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6536. Min Act: -0.0001

Data Index: 790815 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6481. Min Act: -0.0001

Data Index: 397975 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6340. Min Act: -0.0001

Data Index: 723517 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6287. Min Act: -0.0001

Data Index: 227728 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6278. Min Act: -0.0001

Data Index: 9581 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6199. Min Act: -0.0001

Data Index: 253057 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6359. Min Act: -0.0001

Data Index: 828936 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6157. Min Act: -0.0001

Data Index: 246678 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6247. Min Act: -0.0001

Data Index: 720650 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6046. Min Act: -0.0001

Data Index: 667369 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6298. Min Act: -0.0001

Data Index: 424443 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6003. Min Act: -0.0001

Data Index: 827083 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6050. Min Act: -0.0001

Data Index: 116942 (C4 (Web Text))

Max Activating Token Index: 360