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

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

Neuron 2572 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: 0.3641. Min Range: -0.3641

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1085874 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.3129. Min Act: -0.0001

Data Index: 956392 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2833. Min Act: -0.0000

Data Index: 862180 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1234888 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2973. Min Act: -0.0000

Data Index: 259597 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2832. Min Act: -0.0000

Data Index: 771344 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1132452 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2823. Min Act: -0.0000

Data Index: 299305 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2933. Min Act: -0.0000

Data Index: 374813 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2644. Min Act: -0.0000

Data Index: 758498 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2587. Min Act: -0.0001

Data Index: 389285 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2576. Min Act: -0.0001

Data Index: 183711 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1467578 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2435. Min Act: -0.0001

Data Index: 437108 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2752. Min Act: -0.0000

Data Index: 63645 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2477. Min Act: -0.0000

Data Index: 979367 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2444. Min Act: -0.0001

Data Index: 438736 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2441. Min Act: -0.0000

Data Index: 246241 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2345. Min Act: -0.0000

Data Index: 293383 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.3641. Min Range: -0.3641

Max Act: 0.2370. Min Act: -0.0000

Data Index: 359870 (C4 (Web Text))

Max Activating Token Index: 616