Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.6012. Min Act: -0.0000

Data Index: 912740 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.8236. Min Act: -0.0000

Data Index: 1921195 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.4951. Min Act: -0.0000

Data Index: 505065 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.3422. Min Act: -0.0000

Data Index: 594439 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.3407. Min Act: -0.0000

Data Index: 667844 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.4303. Min Act: -0.0000

Data Index: 391087 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.6787. Min Act: -0.0000

Data Index: 1388785 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.0459. Min Act: -0.0000

Data Index: 290692 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9348. Min Act: -0.0000

Data Index: 1201187 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8893. Min Act: -0.0000

Data Index: 138709 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8637. Min Act: -0.0000

Data Index: 658126 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.0306. Min Act: -0.0000

Data Index: 1505477 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8866. Min Act: -0.0000

Data Index: 1701863 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8271. Min Act: -0.0000

Data Index: 263487 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.7819. Min Act: -0.0001

Data Index: 1941455 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.6424. Min Act: -0.0000

Data Index: 1005752 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.7786. Min Act: -0.0000

Data Index: 1347374 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8973. Min Act: -0.0000

Data Index: 120929 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1006776 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8749. Min Act: -0.0000

Data Index: 939004 (The Pile)

Max Activating Token Index: 522