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

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

Neuron 448 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.2236. Min Act: -0.0002

Data Index: 1102392 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0887. Min Act: -0.0002

Data Index: 261330 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0943. Min Act: -0.0002

Data Index: 803026 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0729. Min Act: -0.0002

Data Index: 1161388 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0385. Min Act: -0.0002

Data Index: 1124587 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0567. Min Act: -0.0002

Data Index: 536830 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.2236. Min Range: -2.2236

Max Act: 2.0049. Min Act: -0.0002

Data Index: 657655 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9972. Min Act: -0.0002

Data Index: 100366 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9962. Min Act: -0.0002

Data Index: 457222 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9829. Min Act: -0.0002

Data Index: 1083194 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9298. Min Act: -0.0002

Data Index: 935964 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9399. Min Act: -0.0002

Data Index: 375590 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9356. Min Act: -0.0002

Data Index: 1114849 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9051. Min Act: -0.0002

Data Index: 914375 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.8783. Min Act: -0.0002

Data Index: 849435 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.9151. Min Act: -0.0002

Data Index: 423361 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.8842. Min Act: -0.0002

Data Index: 1271429 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.8699. Min Act: -0.0002

Data Index: 719152 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.8296. Min Act: -0.0002

Data Index: 1341057 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 2.2236. Min Range: -2.2236

Max Act: 1.8421. Min Act: -0.0002

Data Index: 1361 (C4 (Web Text))

Max Activating Token Index: 100