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

Dataset: The Pile

Neuron 430 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: 1.2420. Min Range: -1.2420

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1524268 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1210439 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.1593. Min Act: -0.0000

Data Index: 820385 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.1182. Min Act: -0.0000

Data Index: 505587 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0289. Min Act: -0.0000

Data Index: 536955 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1178467 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1599264 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1361440 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9486. Min Act: -0.0000

Data Index: 336741 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9476. Min Act: -0.0000

Data Index: 614535 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0326. Min Act: -0.0000

Data Index: 324023 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1452405 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0426. Min Act: -0.0000

Data Index: 579599 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1390688 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9981. Min Act: -0.0000

Data Index: 476463 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8707. Min Act: -0.0000

Data Index: 698244 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1362346 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9441. Min Act: -0.0000

Data Index: 797781 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8480. Min Act: -0.0000

Data Index: 337908 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8451. Min Act: -0.0000

Data Index: 592062 (The Pile)

Max Activating Token Index: 371