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

Dataset: The Pile

Neuron 4394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.4238. Min Act: -0.0000

Data Index: 345160 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.4020. Min Act: 0.0000

Data Index: 320164 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3772. Min Act: 0.0000

Data Index: 1088281 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1344602 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1792480 (The Pile)

Max Activating Token Index: 863

Text #5

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3593. Min Act: 0.0000

Data Index: 1829658 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3654. Min Act: -0.0000

Data Index: 870051 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1294865 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3413. Min Act: -0.0000

Data Index: 19520 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3571. Min Act: 0.0000

Data Index: 798567 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3606. Min Act: -0.0000

Data Index: 90608 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1439559 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3363. Min Act: 0.0000

Data Index: 1690497 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1297133 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3225. Min Act: -0.0000

Data Index: 713213 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1550804 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1731789 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3526. Min Act: -0.0000

Data Index: 400108 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1217181 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1308229 (The Pile)

Max Activating Token Index: 290