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

Dataset: The Pile

Neuron 1143 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7320. Min Act: -0.0000

Data Index: 632717 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1367605 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7512. Min Act: -0.0000

Data Index: 362340 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6758. Min Act: -0.0000

Data Index: 90700 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1384229 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1162414 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1162878 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6663. Min Act: -0.0000

Data Index: 113491 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1526026 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6996. Min Act: -0.0000

Data Index: 862727 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6891. Min Act: -0.0000

Data Index: 440604 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6729. Min Act: -0.0000

Data Index: 729520 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1901424 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7103. Min Act: -0.0000

Data Index: 994176 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1925342 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1677321 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6286. Min Act: -0.0000

Data Index: 582571 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6464. Min Act: -0.0000

Data Index: 116847 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5877. Min Act: -0.0000

Data Index: 160957 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6469. Min Act: -0.0000

Data Index: 796287 (The Pile)

Max Activating Token Index: 715