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

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

Neuron 1861 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: 5.5771. Min Range: -5.5771

Max Act: 5.5771. Min Act: -0.0000

Data Index: 101433 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 5.5771. Min Range: -5.5771

Max Act: 5.3081. Min Act: -0.0000

Data Index: 526268 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 5.5771. Min Range: -5.5771

Max Act: 5.2366. Min Act: -0.0000

Data Index: 367063 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 5.5771. Min Range: -5.5771

Max Act: 5.3361. Min Act: -0.0000

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 5.5771. Min Range: -5.5771

Max Act: 5.1513. Min Act: -0.0000

Data Index: 400978 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 5.5771. Min Range: -5.5771

Max Act: 5.1676. Min Act: -0.0000

Data Index: 1066981 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.8123. Min Act: -0.0000

Data Index: 1169002 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.7725. Min Act: -0.0000

Data Index: 458755 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.9152. Min Act: -0.0000

Data Index: 728430 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.7174. Min Act: -0.0000

Data Index: 773860 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.5066. Min Act: -0.0000

Data Index: 25685 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.9332. Min Act: -0.0000

Data Index: 517632 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.1446. Min Act: -0.0000

Data Index: 1273181 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.1546. Min Act: -0.0000

Data Index: 1348557 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.4608. Min Act: -0.0000

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.2796. Min Act: -0.0000

Data Index: 1204027 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.4019. Min Act: -0.0000

Data Index: 501295 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.5537. Min Act: -0.0000

Data Index: 1317505 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.1916. Min Act: -0.0000

Data Index: 262291 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 5.5771. Min Range: -5.5771

Max Act: 4.3557. Min Act: -0.0000

Data Index: 60592 (C4 (Web Text))

Max Activating Token Index: 57