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

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

Neuron 4965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.7508. Min Act: -0.0000

Data Index: 304304 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.4049. Min Act: -0.0000

Data Index: 331807 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.0994. Min Act: -0.0000

Data Index: 756424 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.1327. Min Act: -0.0000

Data Index: 704529 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.1071. Min Act: -0.0000

Data Index: 427700 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.1050. Min Act: -0.0000

Data Index: 555598 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.0192. Min Act: -0.0000

Data Index: 915375 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.0817. Min Act: -0.0000

Data Index: 267937 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9676. Min Act: -0.0000

Data Index: 350451 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1283092 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.7508. Min Range: -1.7508

Max Act: 1.0358. Min Act: 0.0001

Data Index: 417715 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1133531 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9957. Min Act: -0.0000

Data Index: 409046 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9841. Min Act: -0.0000

Data Index: 15362 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1042416 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1131555 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9024. Min Act: -0.0000

Data Index: 726728 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.8953. Min Act: -0.0000

Data Index: 864471 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1132516 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.7508. Min Range: -1.7508

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1136050 (C4 (Web Text))

Max Activating Token Index: 62