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

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

Neuron 3172 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: 0.8531. Min Range: -0.8531

Max Act: 0.7974. Min Act: -0.0001

Data Index: 914057 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.8531. Min Act: -0.0001

Data Index: 753263 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1033841 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1096276 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.5928. Min Act: -0.0001

Data Index: 1209675 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7515. Min Act: -0.0001

Data Index: 994360 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7219. Min Act: -0.0001

Data Index: 694074 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6560. Min Act: -0.0001

Data Index: 866494 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7942. Min Act: -0.0001

Data Index: 121494 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6142. Min Act: -0.0001

Data Index: 1233166 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6391. Min Act: -0.0001

Data Index: 195443 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7327. Min Act: -0.0001

Data Index: 923957 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7049. Min Act: -0.0001

Data Index: 290985 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6041. Min Act: -0.0001

Data Index: 722939 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.7043. Min Act: -0.0001

Data Index: 53313 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6580. Min Act: -0.0001

Data Index: 125089 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.5756. Min Act: -0.0001

Data Index: 317733 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1140821 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6930. Min Act: -0.0001

Data Index: 542271 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.8531. Min Range: -0.8531

Max Act: 0.6364. Min Act: -0.0001

Data Index: 1301130 (C4 (Web Text))

Max Activating Token Index: 237