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

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

Neuron 2318 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: 1.2757. Min Range: -1.2757

Max Act: 1.2757. Min Act: -0.0000

Data Index: 632162 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.2325. Min Act: -0.0000

Data Index: 537587 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9121. Min Act: -0.0000

Data Index: 443339 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9565. Min Act: -0.0000

Data Index: 129091 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8769. Min Act: -0.0000

Data Index: 678520 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9296. Min Act: -0.0000

Data Index: 265969 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1585030 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1129319 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7532. Min Act: -0.0000

Data Index: 777 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1152985 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7916. Min Act: -0.0000

Data Index: 463267 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7715. Min Act: -0.0000

Data Index: 302817 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7518. Min Act: -0.0000

Data Index: 490890 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8042. Min Act: -0.0000

Data Index: 91338 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8533. Min Act: -0.0000

Data Index: 144139 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1456081 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8187. Min Act: -0.0000

Data Index: 870844 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8435. Min Act: -0.0000

Data Index: 902001 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8098. Min Act: -0.0000

Data Index: 676889 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1290385 (C4 (Web Text))

Max Activating Token Index: 320