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

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

Neuron 49 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: 1.4036. Min Range: -1.4036

Max Act: 1.4036. Min Act: -0.0001

Data Index: 226656 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.3267. Min Act: -0.0001

Data Index: 1145850 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2805. Min Act: -0.0001

Data Index: 829094 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2946. Min Act: -0.0001

Data Index: 879611 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2838. Min Act: -0.0001

Data Index: 778872 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2883. Min Act: -0.0001

Data Index: 807541 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2540. Min Act: -0.0001

Data Index: 137939 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2836. Min Act: -0.0001

Data Index: 841003 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2534. Min Act: -0.0001

Data Index: 61661 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2667. Min Act: -0.0001

Data Index: 469853 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2492. Min Act: -0.0001

Data Index: 507076 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2460. Min Act: -0.0001

Data Index: 1278241 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2447. Min Act: -0.0001

Data Index: 731665 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2481. Min Act: -0.0001

Data Index: 54297 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1300775 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1304878 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2258. Min Act: -0.0001

Data Index: 615701 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2393. Min Act: -0.0001

Data Index: 309030 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2276. Min Act: -0.0001

Data Index: 1000837 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.2471. Min Act: -0.0001

Data Index: 1195126 (C4 (Web Text))

Max Activating Token Index: 94