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

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

Neuron 654 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7947. Min Range: -6.7947

Max Act: 6.7947. Min Act: -0.0000

Data Index: 938492 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 6.7947. Min Range: -6.7947

Max Act: 6.3803. Min Act: 0.0000

Data Index: 518901 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.7692. Min Act: -0.0000

Data Index: 1057436 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.9398. Min Act: -0.0000

Data Index: 861212 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.6723. Min Act: -0.0000

Data Index: 1085084 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.7299. Min Act: -0.0000

Data Index: 1090952 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.6708. Min Act: -0.0000

Data Index: 1128439 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.5857. Min Act: -0.0000

Data Index: 1249932 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.4459. Min Act: -0.0000

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.4125. Min Act: -0.0000

Data Index: 852004 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.4033. Min Act: -0.0000

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.4052. Min Act: -0.0000

Data Index: 833972 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.4159. Min Act: 0.0000

Data Index: 829569 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.3858. Min Act: -0.0000

Data Index: 1129486 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.3469. Min Act: -0.0000

Data Index: 338380 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.3433. Min Act: -0.0000

Data Index: 210935 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.3278. Min Act: 0.0000

Data Index: 810963 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.2963. Min Act: -0.0000

Data Index: 691462 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.3059. Min Act: 0.0000

Data Index: 892599 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 6.7947. Min Range: -6.7947

Max Act: 5.0882. Min Act: -0.0000

Data Index: 179088 (C4 (Web Text))

Max Activating Token Index: 156