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

Dataset: The Pile

Neuron 3027 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: 1.3980. Min Range: -1.3980

Max Act: 1.3980. Min Act: -0.0000

Data Index: 913785 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1352371 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0816. Min Act: -0.0000

Data Index: 116058 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1238. Min Act: -0.0000

Data Index: 585083 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1362257 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0622. Min Act: -0.0000

Data Index: 937696 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0224. Min Act: -0.0000

Data Index: 874138 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0138. Min Act: -0.0000

Data Index: 681506 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1844477 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1784918 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1003721 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9404. Min Act: -0.0000

Data Index: 299090 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1872784 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1522845 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9211. Min Act: -0.0000

Data Index: 494098 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1676162 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1126406 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1646368 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1097539 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.3980. Min Range: -1.3980

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1765206 (The Pile)

Max Activating Token Index: 732