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

Dataset: The Pile

Neuron 1958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.8634. Min Act: -0.0000

Data Index: 985518 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1364071 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.8166. Min Act: -0.0000

Data Index: 203072 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.9257. Min Act: -0.0000

Data Index: 696843 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.8060. Min Act: -0.0000

Data Index: 513513 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.8165. Min Act: -0.0000

Data Index: 70649 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1825833 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1076054 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1425798 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1680091 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1614518 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1264234 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7394. Min Act: -0.0000

Data Index: 684581 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1304878 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1829453 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.6940. Min Act: -0.0000

Data Index: 261859 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1517905 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1746886 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.6648. Min Act: -0.0000

Data Index: 176185 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1179463 (The Pile)

Max Activating Token Index: 589