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

Dataset: The Pile

Neuron 3308 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0000

Data Index: 174800 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1936606 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5731. Min Act: 0.0000

Data Index: 1733027 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1563720 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5285. Min Act: -0.0000

Data Index: 303524 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5347. Min Act: -0.0000

Data Index: 897268 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1978760 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1518007 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4635. Min Act: 0.0000

Data Index: 963585 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1203778 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1498962 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1494573 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4476. Min Act: 0.0000

Data Index: 575432 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1548721 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4413. Min Act: 0.0000

Data Index: 1312414 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4272. Min Act: -0.0000

Data Index: 79175 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4303. Min Act: -0.0000

Data Index: 212652 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1661918 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1048246 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4146. Min Act: -0.0000

Data Index: 193264 (The Pile)

Max Activating Token Index: 834