Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2373 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4092. Min Act: -0.0001

Data Index: 236269 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3113. Min Act: -0.0001

Data Index: 266151 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1086446 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2682. Min Act: -0.0001

Data Index: 291435 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2773. Min Act: -0.0001

Data Index: 644398 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2849. Min Act: -0.0001

Data Index: 183304 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2760. Min Act: -0.0001

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2706. Min Act: -0.0000

Data Index: 695341 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2699. Min Act: -0.0001

Data Index: 141616 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2977. Min Act: -0.0001

Data Index: 471239 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2749. Min Act: -0.0001

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2839. Min Act: -0.0001

Data Index: 336463 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2550. Min Act: -0.0001

Data Index: 430152 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1217583 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2610. Min Act: -0.0000

Data Index: 673319 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2690. Min Act: -0.0001

Data Index: 497901 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2819. Min Act: -0.0000

Data Index: 823259 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2379. Min Act: -0.0000

Data Index: 266366 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2721. Min Act: -0.0001

Data Index: 323090 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1306652 (C4 (Web Text))

Max Activating Token Index: 1010