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

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

Neuron 364 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.9094. Min Act: -0.0000

Data Index: 881144 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.5691. Min Act: -0.0000

Data Index: 192217 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.1475. Min Act: -0.0000

Data Index: 593656 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.4445. Min Act: -0.0000

Data Index: 984637 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.4420. Min Act: -0.0000

Data Index: 1239702 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.3078. Min Act: -0.0000

Data Index: 384470 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.8543. Min Act: -0.0001

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.9982. Min Act: -0.0000

Data Index: 1042449 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.9577. Min Act: -0.0000

Data Index: 244246 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.0956. Min Act: -0.0000

Data Index: 1059162 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.1353. Min Act: -0.0000

Data Index: 848332 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.0064. Min Act: -0.0000

Data Index: 1276327 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.9833. Min Act: -0.0000

Data Index: 943014 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 3.9094. Min Range: -3.9094

Max Act: 3.0992. Min Act: -0.0000

Data Index: 920148 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.9259. Min Act: -0.0000

Data Index: 272836 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.9237. Min Act: -0.0000

Data Index: 18860 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.7494. Min Act: -0.0000

Data Index: 8120 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.8442. Min Act: -0.0000

Data Index: 678415 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.8343. Min Act: -0.0000

Data Index: 523601 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.9094. Min Range: -3.9094

Max Act: 2.8289. Min Act: -0.0000

Data Index: 941064 (C4 (Web Text))

Max Activating Token Index: 917