Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2643 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8152. Min Act: -0.0001

Data Index: 233385 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8329. Min Act: -0.0001

Data Index: 460569 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1028235 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6750. Min Act: -0.0001

Data Index: 721258 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6034. Min Act: -0.0001

Data Index: 550341 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6306. Min Act: -0.0001

Data Index: 235264 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6460. Min Act: -0.0001

Data Index: 660835 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6259. Min Act: -0.0001

Data Index: 601413 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5734. Min Act: -0.0001

Data Index: 795681 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5873. Min Act: -0.0001

Data Index: 654290 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6455. Min Act: -0.0001

Data Index: 934811 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5277. Min Act: -0.0001

Data Index: 117711 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5242. Min Act: -0.0001

Data Index: 677198 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5654. Min Act: -0.0001

Data Index: 82975 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5741. Min Act: -0.0001

Data Index: 591548 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5702. Min Act: -0.0001

Data Index: 1356236 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1350671 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.4982. Min Act: -0.0001

Data Index: 113842 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5448. Min Act: -0.0001

Data Index: 301563 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5320. Min Act: -0.0001

Data Index: 638192 (C4 (Web Text))

Max Activating Token Index: 521