Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 9.6215. Min Range: -9.6215

Max Act: 9.6215. Min Act: -0.1700

Data Index: 904450 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 9.6215. Min Range: -9.6215

Max Act: 9.4340. Min Act: -0.1700

Data Index: 859642 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 9.6215. Min Range: -9.6215

Max Act: 9.1840. Min Act: -0.1700

Data Index: 1356040 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 9.6215. Min Range: -9.6215

Max Act: 9.0590. Min Act: -0.1700

Data Index: 317727 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.9965. Min Act: -0.1700

Data Index: 885358 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.9965. Min Act: -0.1700

Data Index: 1180679 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.9965. Min Act: -0.1700

Data Index: 832802 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.8715. Min Act: -0.1700

Data Index: 1351316 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.8090. Min Act: -0.1700

Data Index: 540172 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.8090. Min Act: -0.1700

Data Index: 773497 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.8090. Min Act: -0.1700

Data Index: 659219 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.8090. Min Act: -0.1700

Data Index: 244885 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.6840. Min Act: -0.1700

Data Index: 1575360 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.6840. Min Act: -0.1700

Data Index: 1060168 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.6840. Min Act: -0.1700

Data Index: 225575 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.6840. Min Act: -0.1700

Data Index: 919422 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.6215. Min Act: -0.1700

Data Index: 482997 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.5590. Min Act: -0.1700

Data Index: 1228211 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.5590. Min Act: -0.1700

Data Index: 514158 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 9.6215. Min Range: -9.6215

Max Act: 8.5590. Min Act: -0.1700

Data Index: 962771 (C4 (Web Text))

Max Activating Token Index: 3