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

Dataset: The Pile

Neuron 1728 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: 3.9128. Min Range: -3.9128

Max Act: 3.9128. Min Act: -0.0000

Data Index: 853660 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.7842. Min Act: -0.0000

Data Index: 1450981 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.7773. Min Act: -0.0000

Data Index: 1597009 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.4224. Min Act: -0.0000

Data Index: 922936 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.3355. Min Act: -0.0000

Data Index: 236521 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.2743. Min Act: -0.0000

Data Index: 589190 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.2769. Min Act: -0.0000

Data Index: 366262 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.1037. Min Act: -0.0000

Data Index: 1009548 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.0764. Min Act: -0.0000

Data Index: 1178946 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.1841. Min Act: -0.0000

Data Index: 1815243 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.1955. Min Act: -0.0000

Data Index: 71455 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 3.9128. Min Range: -3.9128

Max Act: 2.9045. Min Act: -0.0000

Data Index: 967758 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.1964. Min Act: -0.0000

Data Index: 1413840 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 3.9128. Min Range: -3.9128

Max Act: 2.9968. Min Act: -0.0000

Data Index: 1913540 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.1081. Min Act: -0.0000

Data Index: 1992723 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.0837. Min Act: -0.0000

Data Index: 707540 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.0845. Min Act: -0.0000

Data Index: 1731502 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.0613. Min Act: -0.0000

Data Index: 1978176 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 3.9128. Min Range: -3.9128

Max Act: 2.7703. Min Act: -0.0000

Data Index: 1830826 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 3.9128. Min Range: -3.9128

Max Act: 3.0591. Min Act: -0.0000

Data Index: 718380 (The Pile)

Max Activating Token Index: 329