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

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

Neuron 4053 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3670. Min Range: -1.3670

Max Act: 1.3670. Min Act: -0.0000

Data Index: 265231 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.3670. Min Range: -1.3670

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1326780 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.7580. Min Act: -0.0000

Data Index: 465171 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1118439 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.7583. Min Act: -0.0000

Data Index: 790895 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.7474. Min Act: -0.0000

Data Index: 308238 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6904. Min Act: -0.0000

Data Index: 873213 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6968. Min Act: -0.0000

Data Index: 906142 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.7310. Min Act: -0.0000

Data Index: 356031 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6835. Min Act: -0.0000

Data Index: 875324 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6411. Min Act: -0.0000

Data Index: 279037 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6994. Min Act: -0.0000

Data Index: 637757 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6601. Min Act: -0.0000

Data Index: 734111 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6480. Min Act: -0.0000

Data Index: 37565 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6055. Min Act: -0.0000

Data Index: 880382 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6424. Min Act: -0.0000

Data Index: 388571 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6329. Min Act: -0.0000

Data Index: 199855 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.5721. Min Act: -0.0000

Data Index: 680804 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6055. Min Act: -0.0000

Data Index: 975586 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.3670. Min Range: -1.3670

Max Act: 0.6177. Min Act: -0.0000

Data Index: 761057 (C4 (Web Text))

Max Activating Token Index: 147