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

Dataset: The Pile

Neuron 3348 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: 3.7601. Min Range: -3.7601

Max Act: 3.7601. Min Act: -0.0000

Data Index: 1943486 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.5703. Min Act: -0.0000

Data Index: 963407 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.3687. Min Act: -0.0000

Data Index: 950601 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2908. Min Act: -0.0000

Data Index: 1014346 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.3996. Min Act: -0.0000

Data Index: 759670 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.1881. Min Act: -0.0000

Data Index: 605886 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.3268. Min Act: -0.0000

Data Index: 1910209 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.3227. Min Act: -0.0000

Data Index: 674322 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.1457. Min Act: -0.0000

Data Index: 192777 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.4329. Min Act: -0.0000

Data Index: 1779953 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.4459. Min Act: -0.0000

Data Index: 1041650 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2746. Min Act: -0.0000

Data Index: 1837191 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.0925. Min Act: -0.0000

Data Index: 184731 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2608. Min Act: -0.0000

Data Index: 95726 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2255. Min Act: -0.0000

Data Index: 937587 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.0831. Min Act: -0.0000

Data Index: 1434829 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2327. Min Act: -0.0000

Data Index: 1415328 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 3.7601. Min Range: -3.7601

Max Act: 2.9032. Min Act: -0.0000

Data Index: 365652 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.3177. Min Act: -0.0000

Data Index: 1609586 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 3.7601. Min Range: -3.7601

Max Act: 3.2048. Min Act: -0.0000

Data Index: 1847969 (The Pile)

Max Activating Token Index: 164