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

Dataset: The Pile

Neuron 265 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: 0.4190. Min Range: -0.4190

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1537217 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3557. Min Act: -0.0000

Data Index: 722241 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1654334 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1048133 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3146. Min Act: -0.0000

Data Index: 445099 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2773. Min Act: -0.0000

Data Index: 362694 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1005209 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1294051 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1024427 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1257908 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1531921 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1475073 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1768872 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1369796 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3053. Min Act: -0.0000

Data Index: 915529 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1466212 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1646696 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2771. Min Act: -0.0000

Data Index: 584396 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2663. Min Act: -0.0000

Data Index: 869093 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1209332 (The Pile)

Max Activating Token Index: 918