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

Dataset: The Pile

Neuron 4370 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.5503. Min Range: -10.5503

Max Act: 10.5503. Min Act: -0.0000

Data Index: 1255139 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 10.5503. Min Range: -10.5503

Max Act: 10.5356. Min Act: -0.0000

Data Index: 819399 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.9410. Min Act: -0.0000

Data Index: 178142 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.9891. Min Act: -0.0000

Data Index: 322071 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.3341. Min Act: -0.0000

Data Index: 162580 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.8403. Min Act: -0.0000

Data Index: 1897377 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.3839. Min Act: -0.0000

Data Index: 99405 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.6457. Min Act: -0.0000

Data Index: 1650505 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.1792. Min Act: -0.0000

Data Index: 491460 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.1030. Min Act: -0.0000

Data Index: 244225 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.1254. Min Act: -0.0000

Data Index: 491966 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.4508. Min Act: -0.0000

Data Index: 519078 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.8923. Min Act: -0.0000

Data Index: 791111 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.9357. Min Act: -0.0000

Data Index: 578422 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.9415. Min Act: -0.0000

Data Index: 1163297 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.4117. Min Act: -0.0000

Data Index: 452571 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.4551. Min Act: -0.0000

Data Index: 489083 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.1299. Min Act: -0.0000

Data Index: 299518 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 10.5503. Min Range: -10.5503

Max Act: 8.3216. Min Act: -0.0000

Data Index: 1172685 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 10.5503. Min Range: -10.5503

Max Act: 9.2994. Min Act: -0.0000

Data Index: 1653522 (The Pile)

Max Activating Token Index: 537