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

Dataset: The Pile

Neuron 3581 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4611. Min Act: -0.0000

Data Index: 470026 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1917980 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1402544 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1899000 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3682. Min Act: -0.0000

Data Index: 842346 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3747. Min Act: -0.0000

Data Index: 24996 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3647. Min Act: -0.0000

Data Index: 570255 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3583. Min Act: -0.0000

Data Index: 578547 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3437. Min Act: -0.0000

Data Index: 417237 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1589776 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1571844 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3399. Min Act: -0.0000

Data Index: 671682 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3338. Min Act: -0.0000

Data Index: 451897 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3030. Min Act: -0.0000

Data Index: 812552 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3235. Min Act: -0.0000

Data Index: 983551 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1291407 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1331400 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3184. Min Act: -0.0000

Data Index: 784783 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3157. Min Act: -0.0000

Data Index: 317692 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1041265 (The Pile)

Max Activating Token Index: 259