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

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

Neuron 3296 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: 0.6322. Min Range: -0.6322

Max Act: 0.6322. Min Act: -0.0001

Data Index: 30496 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5926. Min Act: -0.0001

Data Index: 299051 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5956. Min Act: -0.0001

Data Index: 344428 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.6261. Min Act: -0.0001

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5835. Min Act: -0.0001

Data Index: 338730 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.6006. Min Act: -0.0001

Data Index: 426248 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5377. Min Act: -0.0001

Data Index: 259214 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5644. Min Act: -0.0001

Data Index: 607096 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5403. Min Act: -0.0001

Data Index: 1046363 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4882. Min Act: -0.0001

Data Index: 353511 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4992. Min Act: -0.0001

Data Index: 264707 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4845. Min Act: -0.0001

Data Index: 2038 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5235. Min Act: -0.0001

Data Index: 306928 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4479. Min Act: -0.0001

Data Index: 733771 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1009753 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1276753 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4942. Min Act: -0.0001

Data Index: 414656 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4704. Min Act: -0.0001

Data Index: 1266077 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5053. Min Act: -0.0001

Data Index: 14571 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5217. Min Act: -0.0001

Data Index: 1343515 (C4 (Web Text))

Max Activating Token Index: 703