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

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

Neuron 882 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.7978. Min Act: -0.0001

Data Index: 1202526 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5404. Min Act: -0.0001

Data Index: 844168 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.5369. Min Act: -0.0001

Data Index: 1611224 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4734. Min Act: -0.0001

Data Index: 538 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1364296 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3935. Min Act: -0.0001

Data Index: 165373 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.4124. Min Act: -0.0001

Data Index: 912355 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2434. Min Act: -0.0001

Data Index: 1147655 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3069. Min Act: -0.0001

Data Index: 829497 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2299. Min Act: -0.0001

Data Index: 649189 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2317. Min Act: -0.0001

Data Index: 1088431 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2964. Min Act: -0.0001

Data Index: 266954 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2297. Min Act: -0.0001

Data Index: 911480 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3417. Min Act: -0.0001

Data Index: 199243 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3342. Min Act: -0.0001

Data Index: 758155 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2477. Min Act: -0.0001

Data Index: 1029802 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1638580 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.2657. Min Act: -0.0001

Data Index: 998689 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.1436. Min Act: -0.0001

Data Index: 916354 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.7978. Min Range: -1.7978

Max Act: 1.3522. Min Act: -0.0001

Data Index: 1128455 (C4 (Web Text))

Max Activating Token Index: 214