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

Dataset: The Pile

Neuron 4027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1251022 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1242003 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1584259 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9393. Min Act: -0.0000

Data Index: 382706 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9398. Min Act: -0.0000

Data Index: 229268 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8689. Min Act: -0.0000

Data Index: 200798 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8677. Min Act: -0.0000

Data Index: 122121 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9087. Min Act: -0.0000

Data Index: 231609 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1331964 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8173. Min Act: -0.0000

Data Index: 137758 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1953429 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7653. Min Act: -0.0000

Data Index: 328117 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8230. Min Act: -0.0000

Data Index: 310730 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8596. Min Act: -0.0000

Data Index: 181449 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7517. Min Act: -0.0000

Data Index: 840563 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8163. Min Act: -0.0000

Data Index: 152463 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7299. Min Act: -0.0000

Data Index: 106028 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7489. Min Act: -0.0000

Data Index: 393353 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.6970. Min Act: -0.0000

Data Index: 792558 (The Pile)

Max Activating Token Index: 716

Text #19

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1408582 (The Pile)

Max Activating Token Index: 760