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

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

Neuron 2766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.9150. Min Act: -0.0000

Data Index: 850474 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.8922. Min Act: -0.0001

Data Index: 157853 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6512. Min Act: -0.0001

Data Index: 675368 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6640. Min Act: -0.0001

Data Index: 939346 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6537. Min Act: 0.0001

Data Index: 1314828 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1324372 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1156617 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6382. Min Act: -0.0000

Data Index: 374094 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6352. Min Act: -0.0001

Data Index: 413298 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6547. Min Act: -0.0000

Data Index: 184356 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6336. Min Act: -0.0000

Data Index: 394717 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6053. Min Act: -0.0000

Data Index: 942347 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6258. Min Act: -0.0000

Data Index: 394455 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6163. Min Act: -0.0000

Data Index: 828194 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5876. Min Act: -0.0000

Data Index: 300025 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1241365 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6262. Min Act: -0.0000

Data Index: 416103 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6058. Min Act: -0.0000

Data Index: 951123 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.6061. Min Act: -0.0000

Data Index: 783848 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.9150. Min Range: -0.9150

Max Act: 0.5954. Min Act: -0.0000

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 743