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

Dataset: The Pile

Neuron 1350 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: 0.4951. Min Range: -0.4951

Max Act: 0.4951. Min Act: -0.0000

Data Index: 460291 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1190148 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1889745 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1711506 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4629. Min Act: -0.0000

Data Index: 469237 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4644. Min Act: -0.0000

Data Index: 468315 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1036684 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1675029 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4312. Min Act: -0.0000

Data Index: 629313 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4043. Min Act: -0.0000

Data Index: 336977 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1482370 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4140. Min Act: -0.0000

Data Index: 3838 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1492641 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1652010 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1079215 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3947. Min Act: -0.0000

Data Index: 847710 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3964. Min Act: -0.0000

Data Index: 859730 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1603758 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4054. Min Act: -0.0000

Data Index: 836082 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1015486 (The Pile)

Max Activating Token Index: 730