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

Dataset: The Pile

Neuron 2256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.7104. Min Act: -0.0000

Data Index: 59248 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1550381 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1240307 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.4299. Min Act: -0.0000

Data Index: 180012 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3893. Min Act: -0.0000

Data Index: 346410 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1733696 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3817. Min Act: -0.0000

Data Index: 154811 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1594511 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3557. Min Act: -0.0000

Data Index: 574720 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3671. Min Act: -0.0000

Data Index: 596816 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3291. Min Act: -0.0000

Data Index: 736285 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1342566 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3069. Min Act: -0.0000

Data Index: 266862 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1291408 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3189. Min Act: -0.0000

Data Index: 720962 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1295852 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1425504 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1135203 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.2688. Min Act: -0.0000

Data Index: 825066 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.7104. Min Range: -0.7104

Max Act: 0.2874. Min Act: -0.0000

Data Index: 23907 (The Pile)

Max Activating Token Index: 29