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

Dataset: The Pile

Neuron 2696 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: 5.3208. Min Range: -5.3208

Max Act: 5.3208. Min Act: 0.0000

Data Index: 705144 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 5.3208. Min Range: -5.3208

Max Act: 5.0286. Min Act: -0.0000

Data Index: 1782806 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.9664. Min Act: -0.0000

Data Index: 1069676 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.1083. Min Act: 0.0000

Data Index: 1708925 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 5.3208. Min Range: -5.3208

Max Act: 5.0563. Min Act: 0.0000

Data Index: 645869 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.4263. Min Act: 0.0000

Data Index: 1571588 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.2680. Min Act: -0.0000

Data Index: 268129 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.2602. Min Act: -0.0000

Data Index: 1807146 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.1257. Min Act: -0.0000

Data Index: 724088 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.9377. Min Act: 0.0001

Data Index: 1369077 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.9344. Min Act: -0.0000

Data Index: 688842 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 5.3208. Min Range: -5.3208

Max Act: 4.4370. Min Act: -0.0000

Data Index: 1522198 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.9029. Min Act: -0.0000

Data Index: 1316242 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.7455. Min Act: 0.0000

Data Index: 988356 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.8150. Min Act: 0.0000

Data Index: 825560 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.7964. Min Act: 0.0000

Data Index: 826960 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.5928. Min Act: -0.0000

Data Index: 1602470 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.6307. Min Act: 0.0000

Data Index: 1272810 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.8152. Min Act: -0.0000

Data Index: 506538 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 5.3208. Min Range: -5.3208

Max Act: 3.6939. Min Act: 0.0000

Data Index: 337733 (The Pile)

Max Activating Token Index: 724