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

Dataset: The Pile

Neuron 3331 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1783650 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1115766 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6700. Min Act: -0.0000

Data Index: 30248 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1985317 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6186. Min Act: -0.0000

Data Index: 956980 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6073. Min Act: -0.0000

Data Index: 120354 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1310304 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1534430 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1344426 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1176128 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1367246 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6177. Min Act: -0.0000

Data Index: 944854 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6104. Min Act: -0.0000

Data Index: 799008 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1175399 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5748. Min Act: -0.0000

Data Index: 581923 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5496. Min Act: -0.0000

Data Index: 112096 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5496. Min Act: -0.0000

Data Index: 33097 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5818. Min Act: -0.0000

Data Index: 774476 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1012563 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5544. Min Act: -0.0000

Data Index: 846420 (The Pile)

Max Activating Token Index: 433