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

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

Neuron 3440 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: 7.3804. Min Range: -7.3804

Max Act: 7.3804. Min Act: -0.0001

Data Index: 646649 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 7.3804. Min Range: -7.3804

Max Act: 7.0550. Min Act: -0.0000

Data Index: 1258251 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 7.3804. Min Range: -7.3804

Max Act: 6.7369. Min Act: -0.0001

Data Index: 1232822 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 7.3804. Min Range: -7.3804

Max Act: 6.4267. Min Act: -0.0001

Data Index: 1080271 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 7.3804. Min Range: -7.3804

Max Act: 6.2582. Min Act: -0.0001

Data Index: 1055961 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.9655. Min Act: -0.0001

Data Index: 98162 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.9066. Min Act: -0.0001

Data Index: 997600 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.6734. Min Act: -0.0001

Data Index: 11229 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.4446. Min Act: -0.0001

Data Index: 878379 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.2335. Min Act: -0.0001

Data Index: 310214 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.2908. Min Act: -0.0001

Data Index: 542377 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.5571. Min Act: -0.0001

Data Index: 1275626 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.0920. Min Act: -0.0001

Data Index: 1046718 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.4201. Min Act: -0.0001

Data Index: 876471 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 7.3804. Min Range: -7.3804

Max Act: 4.9647. Min Act: -0.0001

Data Index: 753870 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.0443. Min Act: -0.0001

Data Index: 903585 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 7.3804. Min Range: -7.3804

Max Act: 4.9324. Min Act: -0.0001

Data Index: 312084 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 7.3804. Min Range: -7.3804

Max Act: 5.1312. Min Act: -0.0001

Data Index: 860436 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 7.3804. Min Range: -7.3804

Max Act: 4.8090. Min Act: -0.0001

Data Index: 1154469 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 7.3804. Min Range: -7.3804

Max Act: 4.7155. Min Act: -0.0001

Data Index: 708388 (C4 (Web Text))

Max Activating Token Index: 921