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

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

Neuron 2290 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.7108. Min Act: -0.0000

Data Index: 580345 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.8106. Min Act: -0.0000

Data Index: 984837 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.7328. Min Act: -0.0000

Data Index: 1055457 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.5040. Min Act: -0.0000

Data Index: 636156 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.2558. Min Act: -0.0000

Data Index: 793742 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.4047. Min Act: -0.0000

Data Index: 904266 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.5275. Min Act: -0.0000

Data Index: 282921 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.2374. Min Act: -0.0000

Data Index: 399613 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.3976. Min Act: -0.0000

Data Index: 674692 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.0964. Min Act: -0.0000

Data Index: 701471 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 5.8106. Min Range: -5.8106

Max Act: 5.1101. Min Act: -0.0000

Data Index: 637208 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.8234. Min Act: -0.0000

Data Index: 375228 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.9925. Min Act: -0.0000

Data Index: 227867 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.9981. Min Act: -0.0000

Data Index: 848368 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.7817. Min Act: -0.0000

Data Index: 951091 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.9101. Min Act: -0.0000

Data Index: 1230364 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.6513. Min Act: -0.0000

Data Index: 150015 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.6402. Min Act: -0.0000

Data Index: 1268663 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.7670. Min Act: 0.0000

Data Index: 442871 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 5.8106. Min Range: -5.8106

Max Act: 4.7710. Min Act: -0.0000

Data Index: 897256 (C4 (Web Text))

Max Activating Token Index: 439