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

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

Neuron 4878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.7879. Min Act: -0.0000

Data Index: 1297335 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.6159. Min Act: -0.0001

Data Index: 754323 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.7055. Min Act: -0.0001

Data Index: 1111543 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4464. Min Act: -0.0000

Data Index: 548147 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4327. Min Act: -0.0001

Data Index: 1005842 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.6101. Min Act: -0.0000

Data Index: 1121101 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.5676. Min Act: -0.0000

Data Index: 395748 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3801. Min Act: -0.0000

Data Index: 297028 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4465. Min Act: -0.0000

Data Index: 150575 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4312. Min Act: -0.0000

Data Index: 430476 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.2485. Min Act: -0.0001

Data Index: 203921 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4183. Min Act: -0.0001

Data Index: 1082442 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.4022. Min Act: -0.0000

Data Index: 619760 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3641. Min Act: -0.0000

Data Index: 569371 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.2752. Min Act: -0.0001

Data Index: 876179 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.2042. Min Act: -0.0001

Data Index: 92206 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.1519. Min Act: -0.0000

Data Index: 641227 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1398452 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1271402 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.7879. Min Range: -1.7879

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1026934 (C4 (Web Text))

Max Activating Token Index: 29