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

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

Neuron 859 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5676. Min Range: -4.5676

Max Act: 4.5676. Min Act: -0.0000

Data Index: 813209 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 4.5676. Min Range: -4.5676

Max Act: 4.4243. Min Act: -0.0000

Data Index: 1156964 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.9740. Min Act: -0.0000

Data Index: 1025994 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.6780. Min Act: -0.0000

Data Index: 840939 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.3526. Min Act: -0.0000

Data Index: 68079 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.2759. Min Act: -0.0000

Data Index: 621665 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.2419. Min Act: -0.0000

Data Index: 529068 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.1975. Min Act: -0.0000

Data Index: 908265 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.1710. Min Act: -0.0000

Data Index: 18945 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.2971. Min Act: -0.0000

Data Index: 1111684 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.8422. Min Act: -0.0000

Data Index: 812651 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 4.5676. Min Range: -4.5676

Max Act: 3.0085. Min Act: -0.0000

Data Index: 255424 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.8152. Min Act: -0.0000

Data Index: 243648 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.9389. Min Act: -0.0000

Data Index: 1198823 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.7866. Min Act: -0.0000

Data Index: 926995 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.8671. Min Act: -0.0000

Data Index: 237833 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.6950. Min Act: -0.0000

Data Index: 422982 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.6734. Min Act: -0.0000

Data Index: 395657 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.7979. Min Act: -0.0000

Data Index: 1086962 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 4.5676. Min Range: -4.5676

Max Act: 2.6499. Min Act: -0.0000

Data Index: 51909 (C4 (Web Text))

Max Activating Token Index: 83