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

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

Neuron 3845 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: 1.4078. Min Range: -1.4078

Max Act: 1.3315. Min Act: -0.0000

Data Index: 528963 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1028103 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1457. Min Act: -0.0000

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1398. Min Act: -0.0000

Data Index: 677135 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0353. Min Act: -0.0000

Data Index: 745340 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9988. Min Act: -0.0000

Data Index: 306827 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1188597 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8790. Min Act: -0.0000

Data Index: 66109 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7975. Min Act: -0.0000

Data Index: 685353 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8725. Min Act: -0.0000

Data Index: 672453 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8488. Min Act: -0.0000

Data Index: 806314 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8912. Min Act: -0.0000

Data Index: 257320 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1171654 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8387. Min Act: -0.0000

Data Index: 158716 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7552. Min Act: -0.0000

Data Index: 367985 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8752. Min Act: -0.0000

Data Index: 495078 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7545. Min Act: -0.0000

Data Index: 621008 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7738. Min Act: -0.0000

Data Index: 919413 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7477. Min Act: -0.0000

Data Index: 685557 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7641. Min Act: -0.0000

Data Index: 334739 (C4 (Web Text))

Max Activating Token Index: 94