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

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

Neuron 2853 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: 1.8053. Min Range: -1.8053

Max Act: 1.8053. Min Act: -0.0001

Data Index: 471874 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.7295. Min Act: -0.0001

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.6433. Min Act: -0.0001

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.6651. Min Act: -0.0001

Data Index: 392450 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.6289. Min Act: -0.0001

Data Index: 394670 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.7215. Min Act: -0.0001

Data Index: 204109 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.6577. Min Act: -0.0001

Data Index: 945426 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5671. Min Act: -0.0001

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.7005. Min Act: -0.0001

Data Index: 1010947 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5922. Min Act: -0.0001

Data Index: 1102169 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5922. Min Act: -0.0001

Data Index: 417471 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.4846. Min Act: -0.0001

Data Index: 143619 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5998. Min Act: -0.0001

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5489. Min Act: -0.0001

Data Index: 1020858 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.4867. Min Act: -0.0001

Data Index: 854898 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5328. Min Act: -0.0001

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.5264. Min Act: -0.0001

Data Index: 948087 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.4954. Min Act: -0.0001

Data Index: 1314951 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.4338. Min Act: -0.0001

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.8053. Min Range: -1.8053

Max Act: 1.4668. Min Act: -0.0001

Data Index: 4704 (C4 (Web Text))

Max Activating Token Index: 97