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

Dataset: The Pile

Neuron 2495 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: 5.8053. Min Range: -5.8053

Max Act: 5.8053. Min Act: -0.0000

Data Index: 499178 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.7546. Min Act: -0.0000

Data Index: 1180034 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 5.8053. Min Range: -5.8053

Max Act: 5.0610. Min Act: -0.0000

Data Index: 745142 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 5.8053. Min Range: -5.8053

Max Act: 5.0742. Min Act: -0.0000

Data Index: 756766 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.9721. Min Act: -0.0000

Data Index: 1365059 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.9479. Min Act: -0.0000

Data Index: 1532087 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.9322. Min Act: -0.0000

Data Index: 1742988 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 5.8053. Min Range: -5.8053

Max Act: 5.0891. Min Act: -0.0000

Data Index: 1965502 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.7070. Min Act: -0.0000

Data Index: 215833 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.8271. Min Act: -0.0000

Data Index: 8297 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 5.8053. Min Range: -5.8053

Max Act: 5.0466. Min Act: -0.0000

Data Index: 911624 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.5124. Min Act: -0.0000

Data Index: 198167 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.6656. Min Act: -0.0000

Data Index: 1547214 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.6335. Min Act: -0.0000

Data Index: 227760 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.5993. Min Act: -0.0000

Data Index: 498427 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.8567. Min Act: -0.0000

Data Index: 166897 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.4669. Min Act: -0.0000

Data Index: 1341942 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.4419. Min Act: -0.0000

Data Index: 589319 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.5908. Min Act: -0.0000

Data Index: 370810 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.2103. Min Act: -0.0000

Data Index: 800282 (The Pile)

Max Activating Token Index: 694