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

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

Neuron 822 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: 1.6904. Min Range: -1.6904

Max Act: 1.6904. Min Act: -0.0002

Data Index: 1139840 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.5418. Min Act: -0.0001

Data Index: 57548 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4795. Min Act: -0.0002

Data Index: 1240108 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.2336. Min Act: -0.0002

Data Index: 787532 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.5371. Min Act: -0.0002

Data Index: 268003 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.5866. Min Act: -0.0002

Data Index: 612281 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.5862. Min Act: -0.0001

Data Index: 841846 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4967. Min Act: -0.0002

Data Index: 1193628 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3754. Min Act: -0.0001

Data Index: 46284 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4348. Min Act: -0.0002

Data Index: 74780 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4207. Min Act: -0.0002

Data Index: 667943 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3254. Min Act: -0.0002

Data Index: 869678 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4090. Min Act: -0.0002

Data Index: 311078 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3650. Min Act: -0.0001

Data Index: 1269975 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3175. Min Act: -0.0002

Data Index: 1297296 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3427. Min Act: -0.0002

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.2721. Min Act: -0.0002

Data Index: 1340592 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.0238. Min Act: -0.0002

Data Index: 1246154 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.4944. Min Act: -0.0002

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.6904. Min Range: -1.6904

Max Act: 1.3205. Min Act: -0.0001

Data Index: 445104 (C4 (Web Text))

Max Activating Token Index: 1021