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

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

Neuron 1570 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4401. Min Range: -2.4401

Max Act: 2.4104. Min Act: -0.0000

Data Index: 485604 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.4401. Min Range: -2.4401

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 2.4401. Min Range: -2.4401

Max Act: 2.3057. Min Act: -0.0000

Data Index: 624264 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 2.4401. Min Range: -2.4401

Max Act: 2.4401. Min Act: -0.0000

Data Index: 207739 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.9972. Min Act: -0.0000

Data Index: 406191 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1045085 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7964. Min Act: -0.0000

Data Index: 864139 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.8634. Min Act: -0.0000

Data Index: 850854 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.9382. Min Act: -0.0000

Data Index: 937750 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7417. Min Act: -0.0000

Data Index: 556811 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7301. Min Act: -0.0000

Data Index: 1337692 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.8097. Min Act: -0.0000

Data Index: 544793 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.8947. Min Act: -0.0000

Data Index: 496870 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.8684. Min Act: -0.0000

Data Index: 1127604 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1277461 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7780. Min Act: -0.0000

Data Index: 923020 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1217650 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.7507. Min Act: -0.0000

Data Index: 761860 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.8206. Min Act: -0.0000

Data Index: 390854 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 2.4401. Min Range: -2.4401

Max Act: 1.6269. Min Act: -0.0001

Data Index: 641093 (C4 (Web Text))

Max Activating Token Index: 684