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

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

Neuron 1393 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: 3.2610. Min Range: -3.2610

Max Act: 3.2610. Min Act: -0.0000

Data Index: 435035 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.7239. Min Act: -0.0000

Data Index: 1008164 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.6665. Min Act: -0.0000

Data Index: 341196 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4584. Min Act: -0.0000

Data Index: 1173195 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.5875. Min Act: -0.0000

Data Index: 1130813 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.5378. Min Act: -0.0000

Data Index: 355891 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.3733. Min Act: -0.0000

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.3448. Min Act: -0.0000

Data Index: 114463 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.5736. Min Act: -0.0000

Data Index: 774095 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4346. Min Act: -0.0000

Data Index: 158545 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4335. Min Act: -0.0000

Data Index: 806792 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.3327. Min Act: -0.0000

Data Index: 314245 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4483. Min Act: -0.0000

Data Index: 6119 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.3969. Min Act: -0.0000

Data Index: 526005 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4226. Min Act: -0.0000

Data Index: 184158 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4904. Min Act: -0.0000

Data Index: 490896 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.4096. Min Act: -0.0000

Data Index: 307923 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.5439. Min Act: -0.0000

Data Index: 238469 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.2957. Min Act: -0.0000

Data Index: 163518 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.2610. Min Range: -3.2610

Max Act: 2.3880. Min Act: -0.0000

Data Index: 521077 (C4 (Web Text))

Max Activating Token Index: 397