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

Dataset: The Pile

Neuron 996 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: 3.8466. Min Range: -3.8466

Max Act: 3.8466. Min Act: -0.0000

Data Index: 1277933 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.7749. Min Act: -0.0000

Data Index: 1330935 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.5170. Min Act: -0.0000

Data Index: 818288 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.8052. Min Act: -0.0000

Data Index: 1188866 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.5287. Min Act: -0.0000

Data Index: 1688723 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3709. Min Act: -0.0000

Data Index: 550822 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.6735. Min Act: 0.0001

Data Index: 390506 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3010. Min Act: 0.0001

Data Index: 1167587 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.2754. Min Act: 0.0000

Data Index: 646353 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.4274. Min Act: -0.0000

Data Index: 1200686 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.2278. Min Act: -0.0000

Data Index: 1110641 (The Pile)

Max Activating Token Index: 7

Text #11

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.2288. Min Act: -0.0000

Data Index: 621713 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3843. Min Act: -0.0000

Data Index: 339160 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3821. Min Act: -0.0000

Data Index: 1067962 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3556. Min Act: -0.0000

Data Index: 363830 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3478. Min Act: -0.0000

Data Index: 475824 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3131. Min Act: -0.0000

Data Index: 525789 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3055. Min Act: -0.0000

Data Index: 989546 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.1358. Min Act: -0.0000

Data Index: 701592 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 3.8466. Min Range: -3.8466

Max Act: 3.3176. Min Act: -0.0000

Data Index: 1809291 (The Pile)

Max Activating Token Index: 11