Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1071 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1110785 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0001

Data Index: 190007 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1662. Min Act: -0.0001

Data Index: 395413 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1467. Min Act: -0.0001

Data Index: 351481 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1497. Min Act: -0.0001

Data Index: 487870 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1320. Min Act: -0.0001

Data Index: 42770 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1308. Min Act: -0.0001

Data Index: 311068 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1147955 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1233. Min Act: -0.0001

Data Index: 124922 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1420. Min Act: -0.0001

Data Index: 317241 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0888. Min Act: -0.0001

Data Index: 176966 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1147. Min Act: -0.0001

Data Index: 991209 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0996. Min Act: -0.0001

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1212721 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0937. Min Act: -0.0001

Data Index: 770280 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0920. Min Act: -0.0001

Data Index: 638461 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1059. Min Act: -0.0001

Data Index: 61396 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0949. Min Act: -0.0001

Data Index: 690774 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0870. Min Act: -0.0001

Data Index: 33118 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.0876. Min Act: -0.0001

Data Index: 708473 (C4 (Web Text))

Max Activating Token Index: 567