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

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

Neuron 4066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.7792. Min Act: -0.0001

Data Index: 1358860 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.6394. Min Act: -0.0001

Data Index: 417968 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.5477. Min Act: -0.0001

Data Index: 143763 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.6390. Min Act: -0.0001

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.5812. Min Act: -0.0001

Data Index: 1155884 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.5890. Min Act: -0.0001

Data Index: 952113 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.5038. Min Act: -0.0001

Data Index: 1002988 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4621. Min Act: -0.0001

Data Index: 1175240 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4694. Min Act: -0.0001

Data Index: 959197 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.5028. Min Act: -0.0001

Data Index: 1341340 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4280. Min Act: -0.0001

Data Index: 506213 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4390. Min Act: -0.0001

Data Index: 104867 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3730. Min Act: -0.0001

Data Index: 902164 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4185. Min Act: -0.0001

Data Index: 478845 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.4843. Min Act: -0.0001

Data Index: 949488 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3873. Min Act: -0.0001

Data Index: 1274937 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3817. Min Act: -0.0001

Data Index: 308271 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3842. Min Act: -0.0001

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3406. Min Act: -0.0001

Data Index: 1106935 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.7792. Min Range: -1.7792

Max Act: 1.3814. Min Act: -0.0001

Data Index: 950544 (C4 (Web Text))

Max Activating Token Index: 534