Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6974. Min Act: -0.0001

Data Index: 311535 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5905. Min Act: -0.0001

Data Index: 971543 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5940. Min Act: -0.0000

Data Index: 967330 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5599. Min Act: -0.0000

Data Index: 200800 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6098. Min Act: -0.0000

Data Index: 972594 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5878. Min Act: -0.0000

Data Index: 707220 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1156375 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1217831 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5002. Min Act: -0.0000

Data Index: 558829 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4872. Min Act: -0.0000

Data Index: 274507 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1050768 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4833. Min Act: -0.0000

Data Index: 305169 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4701. Min Act: -0.0000

Data Index: 802141 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4528. Min Act: -0.0001

Data Index: 373476 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4689. Min Act: -0.0000

Data Index: 597081 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1285858 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4807. Min Act: -0.0000

Data Index: 841750 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4540. Min Act: -0.0001

Data Index: 236216 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4800. Min Act: -0.0000

Data Index: 204834 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4630. Min Act: -0.0001

Data Index: 745561 (C4 (Web Text))

Max Activating Token Index: 580