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

Dataset: The Pile

Neuron 4319 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: 3.3474. Min Range: -3.3474

Max Act: 3.3474. Min Act: -0.0000

Data Index: 1577663 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2536. Min Act: -0.0000

Data Index: 839402 (The Pile)

Max Activating Token Index: 657

Text #2

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.9927. Min Act: -0.0000

Data Index: 1157888 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.1053. Min Act: -0.0000

Data Index: 65945 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.0423. Min Act: -0.0000

Data Index: 23382 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8957. Min Act: -0.0000

Data Index: 1707684 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.9591. Min Act: -0.0000

Data Index: 65904 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.9621. Min Act: -0.0000

Data Index: 1084400 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.7638. Min Act: -0.0000

Data Index: 375202 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8836. Min Act: -0.0000

Data Index: 910658 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8482. Min Act: -0.0000

Data Index: 1446729 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1777706 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.7109. Min Act: -0.0000

Data Index: 650216 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8017. Min Act: -0.0000

Data Index: 1856246 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8125. Min Act: -0.0000

Data Index: 646750 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.7527. Min Act: -0.0000

Data Index: 328303 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.7229. Min Act: -0.0000

Data Index: 839223 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.5233. Min Act: -0.0000

Data Index: 203727 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.7951. Min Act: -0.0000

Data Index: 1601789 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.5233. Min Act: -0.0000

Data Index: 1753192 (The Pile)

Max Activating Token Index: 271