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

Dataset: The Pile

Neuron 2676 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: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1994050 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4499. Min Act: -0.0000

Data Index: 617685 (The Pile)

Max Activating Token Index: 864

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4697. Min Act: -0.0000

Data Index: 444266 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1157052 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4223. Min Act: 0.0000

Data Index: 917027 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1123739 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1780211 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4299. Min Act: -0.0000

Data Index: 874121 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4009. Min Act: -0.0000

Data Index: 168835 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4358. Min Act: -0.0000

Data Index: 155105 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4044. Min Act: 0.0000

Data Index: 643896 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3644. Min Act: 0.0000

Data Index: 1377856 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4043. Min Act: -0.0000

Data Index: 507140 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1290377 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1263245 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1748838 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1390985 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1928817 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4014. Min Act: -0.0000

Data Index: 18133 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3903. Min Act: -0.0000

Data Index: 712949 (The Pile)

Max Activating Token Index: 770