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

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

Neuron 3467 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.7962. Min Act: -0.0000

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5240. Min Act: -0.0000

Data Index: 20551 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4709. Min Act: -0.0000

Data Index: 631403 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1216153 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4479. Min Act: -0.0000

Data Index: 97603 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4647. Min Act: -0.0000

Data Index: 620704 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4272. Min Act: -0.0000

Data Index: 830228 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1294196 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4157. Min Act: -0.0000

Data Index: 340859 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1040985 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4306. Min Act: -0.0000

Data Index: 28627 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4168. Min Act: -0.0000

Data Index: 825935 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1279807 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1027182 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4178. Min Act: -0.0000

Data Index: 769696 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4014. Min Act: 0.0000

Data Index: 1124927 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3992. Min Act: -0.0000

Data Index: 602196 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1281312 (C4 (Web Text))

Max Activating Token Index: 992