Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1540 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.6091. Min Act: -0.0001

Data Index: 1359644 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5738. Min Act: -0.0001

Data Index: 690783 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.6123. Min Act: -0.0001

Data Index: 1095953 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5001. Min Act: -0.0001

Data Index: 1570142 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4269. Min Act: -0.0001

Data Index: 1435493 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4452. Min Act: -0.0001

Data Index: 97833 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4580. Min Act: -0.0001

Data Index: 310144 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4555. Min Act: -0.0001

Data Index: 659728 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4064. Min Act: -0.0001

Data Index: 440461 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1062674 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4427. Min Act: -0.0001

Data Index: 321911 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1598910 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3926. Min Act: -0.0001

Data Index: 710984 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4025. Min Act: -0.0001

Data Index: 487537 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4252. Min Act: -0.0001

Data Index: 1157881 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3943. Min Act: -0.0001

Data Index: 146582 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3586. Min Act: -0.0001

Data Index: 229570 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3874. Min Act: -0.0001

Data Index: 70041 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3980. Min Act: -0.0001

Data Index: 41451 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3931. Min Act: -0.0001

Data Index: 143168 (C4 (Web Text))

Max Activating Token Index: 285