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

Dataset: The Pile

Neuron 92 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.9601. Min Act: -0.0000

Data Index: 1895061 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.5559. Min Act: -0.0000

Data Index: 325012 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.4062. Min Act: -0.0000

Data Index: 149481 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1045784 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2420. Min Act: -0.0000

Data Index: 820500 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1141966 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1656314 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.3939. Min Act: -0.0000

Data Index: 283206 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1546582 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1405100 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2157. Min Act: -0.0000

Data Index: 230568 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.1752. Min Act: -0.0000

Data Index: 839600 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1371362 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1824148 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2250. Min Act: -0.0000

Data Index: 197677 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.0112. Min Act: -0.0000

Data Index: 355546 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2314. Min Act: -0.0000

Data Index: 120426 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1095996 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.1538. Min Act: -0.0000

Data Index: 178824 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 1.9601. Min Range: -1.9601

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1107682 (The Pile)

Max Activating Token Index: 314