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

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

Neuron 1749 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.6432. Min Act: -0.0000

Data Index: 524892 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.1944. Min Act: -0.0000

Data Index: 597823 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.2075. Min Act: -0.0000

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.3530. Min Act: -0.0000

Data Index: 850592 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.3186. Min Act: -0.0000

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.0106. Min Act: -0.0000

Data Index: 856745 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9828. Min Act: -0.0000

Data Index: 856466 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9568. Min Act: -0.0000

Data Index: 965627 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9480. Min Act: -0.0000

Data Index: 772999 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9285. Min Act: -0.0000

Data Index: 603113 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.1078. Min Act: -0.0000

Data Index: 59270 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9166. Min Act: -0.0000

Data Index: 1351905 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.8884. Min Act: -0.0000

Data Index: 617124 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.0480. Min Act: -0.0000

Data Index: 289332 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.8533. Min Act: -0.0000

Data Index: 753256 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.0003. Min Act: -0.0000

Data Index: 1234764 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.6260. Min Act: -0.0000

Data Index: 1128243 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 6.6432. Min Range: -6.6432

Max Act: 6.0073. Min Act: -0.0000

Data Index: 754826 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.7712. Min Act: -0.0000

Data Index: 896053 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 6.6432. Min Range: -6.6432

Max Act: 5.9157. Min Act: -0.0000

Data Index: 28649 (C4 (Web Text))

Max Activating Token Index: 510