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

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

Neuron 890 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1432108 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5087. Min Act: -0.0000

Data Index: 546314 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1552096 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1402975 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1604987 (Python Code)

Max Activating Token Index: 853

Text #5

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1570071 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1451263 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1114582 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2788. Min Act: -0.0000

Data Index: 887004 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1459980 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2989. Min Act: -0.0000

Data Index: 752208 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1543954 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1487247 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2250. Min Act: -0.0000

Data Index: 319742 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1642304 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1640045 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1559378 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2599. Min Act: -0.0000

Data Index: 920512 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1515449 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1633769 (Python Code)

Max Activating Token Index: 491