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

Dataset: The Pile

Neuron 2199 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: 0.4916. Min Range: -0.4916

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1270848 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1591419 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4352. Min Act: -0.0000

Data Index: 8680 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4327. Min Act: -0.0000

Data Index: 61313 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4023. Min Act: -0.0000

Data Index: 88628 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1495929 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4168. Min Act: -0.0000

Data Index: 978890 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1353070 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3979. Min Act: -0.0000

Data Index: 821214 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1916345 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1343140 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4569. Min Act: -0.0000

Data Index: 782124 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4212. Min Act: -0.0000

Data Index: 669225 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4065. Min Act: -0.0000

Data Index: 939013 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1038251 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4051. Min Act: -0.0000

Data Index: 778556 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1652376 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3917. Min Act: -0.0000

Data Index: 508654 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1684187 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.4916. Min Range: -0.4916

Max Act: 0.3950. Min Act: -0.0000

Data Index: 147347 (The Pile)

Max Activating Token Index: 473