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

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

Neuron 1152 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.2176. Min Act: -0.0001

Data Index: 233282 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1294210 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1958. Min Act: -0.0001

Data Index: 210182 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1932. Min Act: -0.0001

Data Index: 478556 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1758. Min Act: -0.0001

Data Index: 303092 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1800. Min Act: -0.0001

Data Index: 386111 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1230509 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1640. Min Act: -0.0001

Data Index: 72598 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1651. Min Act: -0.0001

Data Index: 834340 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1312014 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1625. Min Act: -0.0001

Data Index: 987579 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1614. Min Act: -0.0001

Data Index: 537342 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1571. Min Act: -0.0001

Data Index: 664210 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1531. Min Act: -0.0001

Data Index: 831810 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1561. Min Act: -0.0001

Data Index: 217961 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1516. Min Act: -0.0001

Data Index: 592756 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1468. Min Act: -0.0001

Data Index: 156037 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1493. Min Act: -0.0001

Data Index: 401148 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1407. Min Act: -0.0001

Data Index: 489297 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.2199. Min Range: -0.2199

Max Act: 0.1500. Min Act: -0.0001

Data Index: 980179 (C4 (Web Text))

Max Activating Token Index: 728