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

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

Neuron 1321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3803. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3510. Min Act: -0.0001

Data Index: 1236961 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.4315. Min Act: -0.0000

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.5050. Min Act: -0.0001

Data Index: 1142543 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3754. Min Act: -0.0000

Data Index: 1048181 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3754. Min Act: -0.0000

Data Index: 939875 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3765. Min Act: -0.0001

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3786. Min Act: -0.0001

Data Index: 1039126 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.1761. Min Act: -0.0001

Data Index: 934655 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.1446. Min Act: -0.0000

Data Index: 1227454 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3696. Min Act: -0.0000

Data Index: 242939 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3547. Min Act: -0.0000

Data Index: 226855 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.1979. Min Act: -0.0001

Data Index: 742779 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.3058. Min Act: -0.0000

Data Index: 1177463 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.1857. Min Act: -0.0000

Data Index: 376620 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.0417. Min Act: -0.0001

Data Index: 288894 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.0750. Min Act: -0.0000

Data Index: 884376 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 2.5050. Min Range: -2.5050

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1300554 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.0307. Min Act: -0.0000

Data Index: 872181 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 2.5050. Min Range: -2.5050

Max Act: 2.1162. Min Act: -0.0001

Data Index: 505978 (C4 (Web Text))

Max Activating Token Index: 215