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

Dataset: The Pile

Neuron 147 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: 3.8920. Min Range: -3.8920

Max Act: 3.8920. Min Act: -0.0000

Data Index: 238464 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7321. Min Act: -0.0000

Data Index: 1789835 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.8135. Min Act: -0.0000

Data Index: 232621 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.1190. Min Act: -0.0000

Data Index: 1888510 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.2661. Min Act: -0.0000

Data Index: 1458058 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.1451. Min Act: -0.0000

Data Index: 1399218 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.6861. Min Act: -0.0000

Data Index: 1326617 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.0994. Min Act: -0.0000

Data Index: 1738410 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.7249. Min Act: -0.0000

Data Index: 1480105 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1932919 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.6109. Min Act: -0.0000

Data Index: 1537466 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.0189. Min Act: -0.0000

Data Index: 1696056 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.8247. Min Act: -0.0000

Data Index: 983990 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.8066. Min Act: -0.0000

Data Index: 388135 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.0892. Min Act: -0.0000

Data Index: 986096 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.7371. Min Act: -0.0000

Data Index: 1821512 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.8645. Min Act: -0.0000

Data Index: 521279 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.6796. Min Act: -0.0000

Data Index: 409813 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.6101. Min Act: -0.0000

Data Index: 207523 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 3.8920. Min Range: -3.8920

Max Act: 2.1596. Min Act: -0.0000

Data Index: 452269 (The Pile)

Max Activating Token Index: 240