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

Dataset: The Pile

Neuron 1440 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: 1.0949. Min Range: -1.0949

Max Act: 1.0949. Min Act: -0.0000

Data Index: 526633 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.7876. Min Act: -0.0000

Data Index: 695615 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.7273. Min Act: -0.0000

Data Index: 724222 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.7245. Min Act: -0.0000

Data Index: 307045 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.7345. Min Act: -0.0000

Data Index: 846700 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6894. Min Act: -0.0000

Data Index: 191002 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6416. Min Act: -0.0000

Data Index: 306363 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6200. Min Act: -0.0000

Data Index: 404054 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1484347 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1805878 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1297054 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1325801 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1390147 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1959996 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1071586 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5820. Min Act: -0.0000

Data Index: 15606 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1722567 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1173403 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5702. Min Act: -0.0000

Data Index: 480202 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.0949. Min Range: -1.0949

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1512320 (The Pile)

Max Activating Token Index: 423