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

Dataset: The Pile

Neuron 1365 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: 3.5083. Min Range: -3.5083

Max Act: 3.5083. Min Act: -0.0000

Data Index: 1350322 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.3271. Min Act: -0.0000

Data Index: 947457 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.2604. Min Act: -0.0000

Data Index: 335442 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1445931 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1775999 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1878382 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.0354. Min Act: -0.0000

Data Index: 812245 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1741148 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1295791 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1601806 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1688155 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1252361 (The Pile)

Max Activating Token Index: 954

Text #12

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.3235. Min Act: -0.0000

Data Index: 427869 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1553042 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1302160 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.4491. Min Act: -0.0000

Data Index: 715567 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1213034 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1259900 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1189690 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 3.5083. Min Range: -3.5083

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1090290 (The Pile)

Max Activating Token Index: 683