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

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

Neuron 2418 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1271768 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.4264. Min Act: -0.0001

Data Index: 955441 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1283139 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3905. Min Act: -0.0001

Data Index: 699383 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3990. Min Act: -0.0001

Data Index: 234312 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3860. Min Act: -0.0001

Data Index: 1117106 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1317899 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3815. Min Act: -0.0001

Data Index: 896719 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3877. Min Act: -0.0001

Data Index: 254725 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1303031 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3798. Min Act: -0.0001

Data Index: 809507 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3806. Min Act: -0.0001

Data Index: 541815 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3749. Min Act: -0.0001

Data Index: 202278 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3701. Min Act: -0.0001

Data Index: 1093114 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3677. Min Act: -0.0001

Data Index: 982421 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3743. Min Act: -0.0001

Data Index: 991284 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3601. Min Act: -0.0001

Data Index: 347038 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3662. Min Act: -0.0001

Data Index: 147650 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3637. Min Act: -0.0001

Data Index: 2187 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.4290. Min Range: -0.4290

Max Act: 0.3643. Min Act: -0.0001

Data Index: 752957 (C4 (Web Text))

Max Activating Token Index: 780