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

Dataset: The Pile

Neuron 2620 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: 0.6132. Min Range: -0.6132

Max Act: 0.6132. Min Act: -0.0000

Data Index: 913107 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5946. Min Act: -0.0000

Data Index: 145446 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5710. Min Act: -0.0000

Data Index: 153399 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1790505 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1605657 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4688. Min Act: -0.0000

Data Index: 863751 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4951. Min Act: -0.0000

Data Index: 282999 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4671. Min Act: -0.0000

Data Index: 922104 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4908. Min Act: -0.0000

Data Index: 279257 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1958084 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1199741 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1684042 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1036923 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1310856 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4145. Min Act: -0.0000

Data Index: 131554 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1785005 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.3886. Min Act: -0.0000

Data Index: 966220 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4294. Min Act: -0.0000

Data Index: 504302 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1098935 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4434. Min Act: -0.0000

Data Index: 325175 (The Pile)

Max Activating Token Index: 992