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

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

Neuron 1648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.7328. Min Act: -0.0000

Data Index: 297449 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.6955. Min Act: -0.0000

Data Index: 257446 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.6026. Min Act: -0.0000

Data Index: 875651 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.6136. Min Act: -0.0000

Data Index: 917850 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.5879. Min Act: -0.0000

Data Index: 90216 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4938. Min Act: -0.0000

Data Index: 759498 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4698. Min Act: -0.0000

Data Index: 557593 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1159113 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1246689 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.5123. Min Act: -0.0000

Data Index: 878591 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1575459 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4810. Min Act: -0.0000

Data Index: 780765 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4055. Min Act: -0.0000

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4421. Min Act: -0.0000

Data Index: 70122 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1133175 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1036408 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.3480. Min Act: -0.0000

Data Index: 134355 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.3517. Min Act: -0.0000

Data Index: 968947 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.3469. Min Act: -0.0000

Data Index: 724414 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.7328. Min Range: -1.7328

Max Act: 1.4033. Min Act: -0.0000

Data Index: 34418 (C4 (Web Text))

Max Activating Token Index: 27