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

Dataset: The Pile

Neuron 3148 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1499286 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.5983. Min Act: -0.0000

Data Index: 36346 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1607943 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1813165 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1595861 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.3704. Min Act: -0.0000

Data Index: 832442 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1860463 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2991. Min Act: -0.0000

Data Index: 602145 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1875455 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2471. Min Act: -0.0000

Data Index: 123615 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1466077 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1433. Min Act: -0.0000

Data Index: 913423 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1148742 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1206. Min Act: -0.0000

Data Index: 884053 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 1.5983. Min Range: -1.5983

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1106996 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.2260. Min Act: -0.0000

Data Index: 648020 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1728. Min Act: -0.0000

Data Index: 619225 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0963. Min Act: -0.0000

Data Index: 698873 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1260642 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.5983. Min Range: -1.5983

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1855181 (The Pile)

Max Activating Token Index: 602