Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1170169 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1027980 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3922. Min Act: -0.0001

Data Index: 576833 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3639. Min Act: -0.0000

Data Index: 71413 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3488. Min Act: -0.0001

Data Index: 1642244 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3450. Min Act: 0.0000

Data Index: 1295102 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1620572 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1032420 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3361. Min Act: -0.0001

Data Index: 1607165 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3359. Min Act: -0.0001

Data Index: 480442 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1264884 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1008679 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3255. Min Act: -0.0001

Data Index: 226071 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3240. Min Act: -0.0000

Data Index: 796968 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3202. Min Act: -0.0000

Data Index: 337167 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1313567 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1108050 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1055891 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1304891 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3162. Min Act: -0.0000

Data Index: 443077 (C4 (Web Text))

Max Activating Token Index: 24