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

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

Neuron 5854 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 690948 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2723. Min Act: -0.0000

Data Index: 167482 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1041226 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2662. Min Act: -0.0000

Data Index: 263615 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2863. Min Act: -0.0000

Data Index: 809915 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2626. Min Act: -0.0000

Data Index: 570553 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2430. Min Act: -0.0000

Data Index: 915708 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2379. Min Act: -0.0000

Data Index: 439086 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2161. Min Act: -0.0000

Data Index: 207513 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1200525 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2181. Min Act: -0.0000

Data Index: 116047 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2337. Min Act: -0.0000

Data Index: 657146 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2185. Min Act: -0.0000

Data Index: 314503 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2209. Min Act: -0.0000

Data Index: 356410 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1309503 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2106. Min Act: -0.0000

Data Index: 326514 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2104. Min Act: -0.0000

Data Index: 730368 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2033. Min Act: 0.0000

Data Index: 770619 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2121. Min Act: -0.0000

Data Index: 311903 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1939. Min Act: -0.0000

Data Index: 558506 (C4 (Web Text))

Max Activating Token Index: 477