Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 561 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3045. Min Act: -0.0001

Data Index: 22947 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1313477 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3140. Min Act: -0.0000

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1292352 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2836. Min Act: -0.0001

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2662. Min Act: -0.0000

Data Index: 429072 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1187992 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1212263 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2723. Min Act: -0.0000

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1180474 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1587813 (Python Code)

Max Activating Token Index: 440

Text #12

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2586. Min Act: -0.0001

Data Index: 728973 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2599. Min Act: -0.0000

Data Index: 812113 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2629. Min Act: -0.0001

Data Index: 17666 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2312. Min Act: -0.0000

Data Index: 416050 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2474. Min Act: -0.0000

Data Index: 266834 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1044715 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1267769 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2422. Min Act: -0.0001

Data Index: 27395 (C4 (Web Text))

Max Activating Token Index: 94