Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1598. Min Act: -0.0001

Data Index: 415607 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1127025 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1562. Min Act: -0.0001

Data Index: 315682 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1418. Min Act: -0.0001

Data Index: 665028 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1449. Min Act: -0.0001

Data Index: 243003 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1040546 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1312. Min Act: -0.0001

Data Index: 60821 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1315. Min Act: -0.0001

Data Index: 317077 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1258. Min Act: -0.0001

Data Index: 343991 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1010071 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1261. Min Act: -0.0001

Data Index: 717161 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1165. Min Act: -0.0001

Data Index: 24854 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1146. Min Act: -0.0001

Data Index: 218530 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1073. Min Act: -0.0001

Data Index: 998920 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1338810 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1108. Min Act: -0.0001

Data Index: 457603 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1036659 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1102. Min Act: -0.0001

Data Index: 492721 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1097. Min Act: -0.0001

Data Index: 924113 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.1598. Min Range: -0.1598

Max Act: 0.1089. Min Act: -0.0001

Data Index: 488403 (C4 (Web Text))

Max Activating Token Index: 91