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

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

Neuron 2343 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3272. Min Act: -0.0001

Data Index: 672250 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3062. Min Act: -0.0001

Data Index: 361338 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1283056 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2912. Min Act: -0.0001

Data Index: 843088 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2969. Min Act: -0.0001

Data Index: 709045 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3181. Min Act: -0.0001

Data Index: 621150 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2910. Min Act: -0.0001

Data Index: 216145 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1303070 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2778. Min Act: -0.0001

Data Index: 430895 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2944. Min Act: -0.0001

Data Index: 132691 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1309963 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1267614 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2711. Min Act: -0.0001

Data Index: 512081 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2775. Min Act: -0.0001

Data Index: 1289757 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1027642 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2763. Min Act: -0.0001

Data Index: 969531 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2677. Min Act: -0.0001

Data Index: 364783 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2681. Min Act: -0.0001

Data Index: 923234 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1154845 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.3272. Min Range: -0.3272

Max Act: 0.2683. Min Act: -0.0001

Data Index: 538691 (C4 (Web Text))

Max Activating Token Index: 1005