Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2292 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1410828 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4867. Min Act: -0.0000

Data Index: 540177 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1575744 (The Pile)

Max Activating Token Index: 708

Text #3

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4484. Min Act: -0.0000

Data Index: 396717 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1293267 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4072. Min Act: -0.0000

Data Index: 713926 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1705874 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3718. Min Act: -0.0000

Data Index: 225914 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1642453 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1329519 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3534. Min Act: -0.0000

Data Index: 787741 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3260. Min Act: -0.0000

Data Index: 981394 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1359941 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1424812 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3326. Min Act: -0.0000

Data Index: 818854 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3410. Min Act: -0.0000

Data Index: 144786 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1425398 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3362. Min Act: -0.0000

Data Index: 791199 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3214. Min Act: -0.0000

Data Index: 950112 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1706348 (The Pile)

Max Activating Token Index: 974