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

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

Neuron 3618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0024. Min Act: -0.0000

Data Index: 468922 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1001070 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.8914. Min Act: -0.0000

Data Index: 823998 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1377987 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1388191 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.6983. Min Act: -0.0000

Data Index: 262984 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1584417 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1322579 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4859. Min Act: -0.0000

Data Index: 301658 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4800. Min Act: -0.0000

Data Index: 257744 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.5192. Min Act: -0.0000

Data Index: 1515187 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1227174 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4438. Min Act: -0.0000

Data Index: 356314 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4822. Min Act: -0.0000

Data Index: 331205 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4796. Min Act: -0.0000

Data Index: 38311 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4507. Min Act: -0.0000

Data Index: 496281 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1228030 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1189273 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.4167. Min Act: -0.0000

Data Index: 1029195 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.5167. Min Act: -0.0000

Data Index: 764703 (C4 (Web Text))

Max Activating Token Index: 302