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

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

Neuron 3665 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7478. Min Act: -0.0000

Data Index: 970824 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7276. Min Act: -0.0000

Data Index: 27678 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1253728 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7591. Min Act: -0.0001

Data Index: 924738 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1166930 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1013840 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7133. Min Act: -0.0000

Data Index: 153353 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7395. Min Act: -0.0000

Data Index: 457057 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7193. Min Act: -0.0000

Data Index: 409957 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7381. Min Act: -0.0001

Data Index: 93504 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1252343 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7042. Min Act: -0.0000

Data Index: 767769 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7463. Min Act: -0.0001

Data Index: 870783 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1070990 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1011176 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7233. Min Act: -0.0000

Data Index: 374245 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7000. Min Act: -0.0001

Data Index: 366764 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.7091. Min Act: -0.0000

Data Index: 510505 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1065092 (C4 (Web Text))

Max Activating Token Index: 158