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

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

Neuron 834 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: 0.5825. Min Act: -0.0000

Data Index: 1283872 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5067. Min Act: -0.0001

Data Index: 1195351 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5221. Min Act: -0.0001

Data Index: 989551 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5178. Min Act: -0.0000

Data Index: 548067 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1329909 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4939. Min Act: 0.0001

Data Index: 483475 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1049247 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4804. Min Act: -0.0001

Data Index: 570747 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4806. Min Act: -0.0000

Data Index: 903882 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4755. Min Act: -0.0001

Data Index: 454900 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4743. Min Act: -0.0000

Data Index: 638833 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4593. Min Act: -0.0001

Data Index: 391298 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4689. Min Act: -0.0001

Data Index: 329134 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4825. Min Act: -0.0001

Data Index: 1223001 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1038568 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4562. Min Act: -0.0001

Data Index: 44806 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4691. Min Act: -0.0001

Data Index: 1340919 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4512. Min Act: -0.0000

Data Index: 951778 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1009271 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4457. Min Act: -0.0001

Data Index: 351645 (C4 (Web Text))

Max Activating Token Index: 171