Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4293 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.5968. Min Act: -0.0000

Data Index: 1321434 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.8206. Min Act: -0.0000

Data Index: 1190788 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.2721. Min Act: -0.0000

Data Index: 186214 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.0808. Min Act: -0.0000

Data Index: 723369 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.2841. Min Act: -0.0000

Data Index: 52437 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.0524. Min Act: -0.0000

Data Index: 613820 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.3126. Min Act: -0.0000

Data Index: 1111301 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.2043. Min Act: -0.0000

Data Index: 543260 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.1182. Min Act: -0.0000

Data Index: 733042 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.9325. Min Act: -0.0000

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.2349. Min Act: -0.0000

Data Index: 541604 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.8906. Min Act: -0.0000

Data Index: 976478 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.8211. Min Act: -0.0000

Data Index: 1125130 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.8424. Min Act: -0.0000

Data Index: 605990 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 4.5968. Min Range: -4.5968

Max Act: 3.1667. Min Act: -0.0000

Data Index: 256016 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.7159. Min Act: -0.0000

Data Index: 1262049 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.6984. Min Act: -0.0000

Data Index: 468513 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.9101. Min Act: -0.0000

Data Index: 92192 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.8741. Min Act: -0.0000

Data Index: 192494 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 4.5968. Min Range: -4.5968

Max Act: 2.7383. Min Act: -0.0000

Data Index: 394993 (C4 (Web Text))

Max Activating Token Index: 497