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

Dataset: The Pile

Neuron 111 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: 5.7010. Min Range: -5.7010

Max Act: 5.7010. Min Act: -0.0000

Data Index: 257007 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2833. Min Act: -0.0000

Data Index: 35332 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.0150. Min Act: -0.0000

Data Index: 236580 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.9103. Min Act: -0.0000

Data Index: 183163 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.9686. Min Act: -0.0000

Data Index: 1112872 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.8467. Min Act: -0.0000

Data Index: 1887503 (The Pile)

Max Activating Token Index: 809

Text #6

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.5401. Min Act: -0.0000

Data Index: 1346768 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.4447. Min Act: -0.0000

Data Index: 1143506 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.4115. Min Act: -0.0000

Data Index: 1441329 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.2609. Min Act: -0.0000

Data Index: 1085505 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.3175. Min Act: -0.0000

Data Index: 1828870 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.2489. Min Act: -0.0000

Data Index: 1107728 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.0081. Min Act: -0.0000

Data Index: 491362 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.1574. Min Act: -0.0000

Data Index: 740106 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.5164. Min Act: -0.0000

Data Index: 1336720 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.0631. Min Act: -0.0000

Data Index: 181555 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 5.7010. Min Range: -5.7010

Max Act: 4.0413. Min Act: -0.0000

Data Index: 1771841 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 5.7010. Min Range: -5.7010

Max Act: 3.8353. Min Act: -0.0000

Data Index: 972302 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 5.7010. Min Range: -5.7010

Max Act: 3.9616. Min Act: -0.0000

Data Index: 1187056 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 5.7010. Min Range: -5.7010

Max Act: 3.9813. Min Act: -0.0000

Data Index: 548484 (The Pile)

Max Activating Token Index: 1005