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

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

Neuron 4543 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0483. Min Range: -1.0483

Max Act: 1.0483. Min Act: -0.0001

Data Index: 960597 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.9102. Min Act: -0.0001

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5450. Min Act: -0.0001

Data Index: 861705 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5299. Min Act: -0.0001

Data Index: 317411 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.6514. Min Act: -0.0001

Data Index: 809644 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4427. Min Act: -0.0001

Data Index: 582083 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4848. Min Act: -0.0001

Data Index: 844277 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5567. Min Act: -0.0001

Data Index: 1154809 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5162. Min Act: -0.0001

Data Index: 137830 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5473. Min Act: -0.0001

Data Index: 354547 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5012. Min Act: -0.0001

Data Index: 511942 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4428. Min Act: -0.0001

Data Index: 639881 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4250. Min Act: -0.0001

Data Index: 145115 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4113. Min Act: -0.0001

Data Index: 904978 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4368. Min Act: -0.0001

Data Index: 83441 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4333. Min Act: -0.0001

Data Index: 518758 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4427. Min Act: -0.0001

Data Index: 955245 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.3998. Min Act: -0.0001

Data Index: 756986 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.5150. Min Act: -0.0001

Data Index: 273455 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.0483. Min Range: -1.0483

Max Act: 0.4294. Min Act: -0.0001

Data Index: 998720 (C4 (Web Text))

Max Activating Token Index: 305