Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5446. Min Act: -0.0001

Data Index: 703031 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1154394 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5785. Min Act: -0.0001

Data Index: 206933 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5174. Min Act: -0.0001

Data Index: 873746 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4688. Min Act: -0.0001

Data Index: 745542 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4897. Min Act: -0.0001

Data Index: 850911 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4774. Min Act: -0.0001

Data Index: 349954 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1038866 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4613. Min Act: -0.0001

Data Index: 35914 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4911. Min Act: -0.0001

Data Index: 871504 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4848. Min Act: -0.0001

Data Index: 4784 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4463. Min Act: -0.0001

Data Index: 852740 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4641. Min Act: -0.0001

Data Index: 894502 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1284115 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4378. Min Act: -0.0001

Data Index: 1155057 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4555. Min Act: -0.0001

Data Index: 306868 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3911. Min Act: -0.0000

Data Index: 869664 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1038740 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4025. Min Act: -0.0000

Data Index: 102894 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1032584 (C4 (Web Text))

Max Activating Token Index: 62