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

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

Neuron 2897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1647842 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1643515 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5876. Min Act: -0.0001

Data Index: 1425139 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1568468 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1624549 (Python Code)

Max Activating Token Index: 756

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5068. Min Act: -0.0001

Data Index: 1431690 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1656658 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4906. Min Act: -0.0001

Data Index: 1361042 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1537616 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1580640 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4537. Min Act: -0.0001

Data Index: 1461925 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1571417 (Python Code)

Max Activating Token Index: 849

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4550. Min Act: -0.0001

Data Index: 1493495 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1439737 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4468. Min Act: -0.0001

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1418791 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4554. Min Act: -0.0001

Data Index: 1391398 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4238. Min Act: -0.0001

Data Index: 1373131 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1530037 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1470017 (Python Code)

Max Activating Token Index: 340