Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4787 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5552. Min Act: -0.0000

Data Index: 126296 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.5506. Min Act: -0.0000

Data Index: 749603 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4875. Min Act: -0.0000

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4325. Min Act: -0.0000

Data Index: 61193 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4079. Min Act: -0.0000

Data Index: 560044 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4577. Min Act: -0.0000

Data Index: 786138 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1038541 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4227. Min Act: -0.0000

Data Index: 209045 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4197. Min Act: -0.0000

Data Index: 773508 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4140. Min Act: -0.0000

Data Index: 687114 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4116. Min Act: -0.0000

Data Index: 411149 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3998. Min Act: -0.0000

Data Index: 125556 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3868. Min Act: -0.0000

Data Index: 415520 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4231. Min Act: -0.0000

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1129893 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4127. Min Act: -0.0000

Data Index: 425472 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3756. Min Act: -0.0000

Data Index: 503545 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1084763 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.5552. Min Range: -0.5552

Max Act: 0.3662. Min Act: -0.0000

Data Index: 603463 (C4 (Web Text))

Max Activating Token Index: 812