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

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

Neuron 977 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1352516 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.7485. Min Act: -0.0000

Data Index: 261782 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.5534. Min Act: -0.0000

Data Index: 44720 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1194341 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2979. Min Act: -0.0000

Data Index: 781057 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2038. Min Act: -0.0000

Data Index: 101811 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1061694 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2777. Min Act: -0.0000

Data Index: 45148 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2663. Min Act: -0.0000

Data Index: 307552 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1231867 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1104344 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2429. Min Act: -0.0000

Data Index: 65587 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1046647 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2159. Min Act: -0.0000

Data Index: 7733 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2136. Min Act: -0.0000

Data Index: 832633 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2119. Min Act: -0.0000

Data Index: 849421 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2108. Min Act: -0.0000

Data Index: 17969 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1019883 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2099. Min Act: -0.0000

Data Index: 717220 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.7485. Min Range: -1.7485

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1155175 (C4 (Web Text))

Max Activating Token Index: 967