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

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

Neuron 1952 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.5899. Min Act: -0.0000

Data Index: 345257 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.6101. Min Act: -0.0000

Data Index: 814448 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.2571. Min Act: -0.0000

Data Index: 713048 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1102300 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1126735 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1169374 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0901. Min Act: -0.0000

Data Index: 476688 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0816. Min Act: -0.0000

Data Index: 458607 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0151. Min Act: -0.0000

Data Index: 465835 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1097057 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0768. Min Act: -0.0000

Data Index: 381204 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9082. Min Act: -0.0000

Data Index: 980568 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9662. Min Act: -0.0000

Data Index: 4759 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0163. Min Act: -0.0000

Data Index: 879035 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0979. Min Act: -0.0000

Data Index: 229537 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9024. Min Act: -0.0000

Data Index: 918956 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9596. Min Act: -0.0000

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.8947. Min Act: -0.0000

Data Index: 284382 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9416. Min Act: -0.0000

Data Index: 679170 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9441. Min Act: -0.0000

Data Index: 716278 (C4 (Web Text))

Max Activating Token Index: 774