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

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

Neuron 427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2729. Min Range: -1.2729

Max Act: 1.2729. Min Act: -0.0000

Data Index: 160194 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.2729. Min Range: -1.2729

Max Act: 1.1349. Min Act: -0.0000

Data Index: 82458 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9890. Min Act: -0.0000

Data Index: 643532 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 1.2729. Min Range: -1.2729

Max Act: 1.0442. Min Act: -0.0000

Data Index: 173770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9084. Min Act: -0.0000

Data Index: 494474 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9450. Min Act: -0.0000

Data Index: 490937 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8918. Min Act: -0.0000

Data Index: 253027 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9247. Min Act: -0.0000

Data Index: 475493 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1358754 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8636. Min Act: -0.0000

Data Index: 943616 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8296. Min Act: -0.0000

Data Index: 362639 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9321. Min Act: -0.0000

Data Index: 808993 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1092687 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8179. Min Act: -0.0000

Data Index: 53813 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8045. Min Act: -0.0000

Data Index: 173998 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.9092. Min Act: -0.0000

Data Index: 481840 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8343. Min Act: -0.0000

Data Index: 147348 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1307628 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8197. Min Act: -0.0000

Data Index: 464784 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.2729. Min Range: -1.2729

Max Act: 0.8188. Min Act: -0.0000

Data Index: 31023 (C4 (Web Text))

Max Activating Token Index: 700