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

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

Neuron 4886 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0939. Min Range: -1.0939

Max Act: 1.0939. Min Act: -0.0000

Data Index: 991493 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0939. Min Range: -1.0939

Max Act: 1.0719. Min Act: -0.0000

Data Index: 148550 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.0939. Min Range: -1.0939

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1265928 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1191405 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.9139. Min Act: -0.0000

Data Index: 758012 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1325108 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1157165 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7144. Min Act: -0.0000

Data Index: 555800 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7099. Min Act: -0.0000

Data Index: 42411 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1233985 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.7079. Min Act: -0.0000

Data Index: 282856 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1284510 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6556. Min Act: -0.0000

Data Index: 774056 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1300345 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6157. Min Act: -0.0000

Data Index: 670680 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1074055 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6485. Min Act: -0.0000

Data Index: 656198 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6174. Min Act: -0.0000

Data Index: 723906 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1019489 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1168440 (C4 (Web Text))

Max Activating Token Index: 943