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

Dataset: The Pile

Neuron 406 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1688078 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4082. Min Act: -0.0000

Data Index: 51465 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3863. Min Act: -0.0000

Data Index: 330104 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.4252. Min Act: -0.0000

Data Index: 702669 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3652. Min Act: -0.0000

Data Index: 799968 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3416. Min Act: -0.0000

Data Index: 589948 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3728. Min Act: -0.0000

Data Index: 252716 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3359. Min Act: -0.0000

Data Index: 572682 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3906. Min Act: -0.0000

Data Index: 346665 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1123107 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3398. Min Act: -0.0000

Data Index: 207665 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1492101 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3449. Min Act: -0.0000

Data Index: 70061 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3427. Min Act: -0.0000

Data Index: 703490 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1106948 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1919489 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1660727 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3304. Min Act: -0.0000

Data Index: 423343 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1543373 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.5977. Min Range: -0.5977

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1251057 (The Pile)

Max Activating Token Index: 306