Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.4705. Min Act: -0.0000

Data Index: 994871 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1093202 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1546178 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1044491 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.2161. Min Act: -0.0000

Data Index: 873651 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0945. Min Act: 0.0000

Data Index: 1724498 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1089824 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1458201 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1902600 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9801. Min Act: -0.0000

Data Index: 944640 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9872. Min Act: -0.0000

Data Index: 319795 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0743. Min Act: -0.0000

Data Index: 673228 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1014053 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9241. Min Act: -0.0000

Data Index: 493191 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9148. Min Act: -0.0000

Data Index: 470232 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1220008 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 1.4705. Min Range: -1.4705

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1171313 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1485052 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9452. Min Act: -0.0000

Data Index: 255217 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 1.4705. Min Range: -1.4705

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1346543 (The Pile)

Max Activating Token Index: 884