Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2770 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1056933 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1323449 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1144516 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4095. Min Act: -0.0000

Data Index: 853129 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3937. Min Act: -0.0000

Data Index: 952413 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3620. Min Act: -0.0000

Data Index: 367087 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3809. Min Act: -0.0000

Data Index: 670958 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1012718 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3493. Min Act: -0.0000

Data Index: 152562 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1306360 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3422. Min Act: -0.0000

Data Index: 634630 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3435. Min Act: -0.0000

Data Index: 207691 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3295. Min Act: -0.0000

Data Index: 489994 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3309. Min Act: -0.0000

Data Index: 714433 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3251. Min Act: -0.0000

Data Index: 900192 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3215. Min Act: -0.0000

Data Index: 623829 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3205. Min Act: -0.0000

Data Index: 644316 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1367551 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1355916 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1470076 (Python Code)

Max Activating Token Index: 864