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

Dataset: The Pile

Neuron 463 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9803. Min Act: -0.0000

Data Index: 976373 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9393. Min Act: -0.0000

Data Index: 398386 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9235. Min Act: -0.0000

Data Index: 744943 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1779045 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1601733 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8890. Min Act: -0.0000

Data Index: 312128 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1351540 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8593. Min Act: -0.0000

Data Index: 281120 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8921. Min Act: -0.0000

Data Index: 105597 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1422221 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1651442 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1961684 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1300074 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1209576 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1379596 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8240. Min Act: -0.0000

Data Index: 694372 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1310964 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8388. Min Act: -0.0000

Data Index: 753567 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8181. Min Act: -0.0000

Data Index: 23866 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8394. Min Act: -0.0000

Data Index: 138929 (The Pile)

Max Activating Token Index: 391