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

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

Neuron 4699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1569926 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.3619. Min Act: -0.0000

Data Index: 139240 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.5208. Min Act: -0.0000

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1416543 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1614827 (Python Code)

Max Activating Token Index: 372

Text #6

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.2958. Min Act: -0.0000

Data Index: 1505422 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1587382 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1388281 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1538183 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1545274 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1384974 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1307. Min Act: -0.0000

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1624368 (Python Code)

Max Activating Token Index: 299

Text #14

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1463066 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.0599. Min Act: -0.0000

Data Index: 313064 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.0398. Min Act: -0.0000

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1511088 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1443299 (Python Code)

Max Activating Token Index: 645

Text #19

Max Range: 1.7803. Min Range: -1.7803

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1647229 (Python Code)

Max Activating Token Index: 920