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

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

Neuron 2716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.7120. Min Range: -10.7120

Max Act: 10.7120. Min Act: -0.0000

Data Index: 1110944 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 10.7120. Min Range: -10.7120

Max Act: 9.1816. Min Act: -0.0000

Data Index: 700202 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 10.7120. Min Range: -10.7120

Max Act: 9.0199. Min Act: -0.0000

Data Index: 204057 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.8345. Min Act: -0.0000

Data Index: 208572 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.3739. Min Act: -0.0000

Data Index: 798355 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.5293. Min Act: -0.0000

Data Index: 1075779 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.2471. Min Act: -0.0000

Data Index: 1084446 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.3706. Min Act: -0.0000

Data Index: 602349 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.6587. Min Act: -0.0000

Data Index: 1271544 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.1414. Min Act: -0.0000

Data Index: 1312228 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.4107. Min Act: -0.0000

Data Index: 125243 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.1132. Min Act: -0.0000

Data Index: 573597 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 10.7120. Min Range: -10.7120

Max Act: 7.7182. Min Act: -0.0000

Data Index: 680873 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 10.7120. Min Range: -10.7120

Max Act: 7.9463. Min Act: -0.0000

Data Index: 388793 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.0774. Min Act: -0.0000

Data Index: 866293 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.2210. Min Act: -0.0000

Data Index: 293223 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 10.7120. Min Range: -10.7120

Max Act: 8.0430. Min Act: -0.0000

Data Index: 506456 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 10.7120. Min Range: -10.7120

Max Act: 7.6507. Min Act: -0.0000

Data Index: 1034074 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 10.7120. Min Range: -10.7120

Max Act: 7.7377. Min Act: -0.0000

Data Index: 473260 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 10.7120. Min Range: -10.7120

Max Act: 7.4784. Min Act: -0.0000

Data Index: 1207854 (C4 (Web Text))

Max Activating Token Index: 549