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

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

Neuron 4068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8091. Min Act: -0.0000

Data Index: 77891 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8221. Min Act: -0.0000

Data Index: 581522 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.8551. Min Act: -0.0000

Data Index: 418362 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7979. Min Act: -0.0000

Data Index: 445850 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7647. Min Act: -0.0000

Data Index: 344412 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6862. Min Act: -0.0000

Data Index: 382617 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1002097 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.7087. Min Act: -0.0000

Data Index: 885356 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6985. Min Act: -0.0000

Data Index: 6174 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1117747 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6199. Min Act: -0.0000

Data Index: 964826 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6599. Min Act: -0.0000

Data Index: 226057 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1327984 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1115815 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5759. Min Act: -0.0000

Data Index: 880476 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5730. Min Act: -0.0000

Data Index: 173866 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6026. Min Act: -0.0000

Data Index: 354015 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5798. Min Act: -0.0000

Data Index: 7394 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.6162. Min Act: -0.0000

Data Index: 21361 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.8551. Min Range: -0.8551

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1320310 (C4 (Web Text))

Max Activating Token Index: 123