Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1122007 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0518. Min Act: -0.0001

Data Index: 976751 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1084503 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1183114 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1065477 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0463. Min Act: -0.0001

Data Index: 822012 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0449. Min Act: -0.0001

Data Index: 165775 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1138241 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0445. Min Act: -0.0001

Data Index: 996546 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1296179 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0418. Min Act: -0.0001

Data Index: 230709 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0433. Min Act: -0.0001

Data Index: 912906 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0374. Min Act: -0.0001

Data Index: 438255 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1218407 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0410. Min Act: -0.0001

Data Index: 880429 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0436. Min Act: -0.0001

Data Index: 856271 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0001

Data Index: 161511 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0410. Min Act: -0.0001

Data Index: 421897 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0404. Min Act: -0.0001

Data Index: 604423 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0398. Min Act: -0.0001

Data Index: 170114 (C4 (Web Text))

Max Activating Token Index: 326