Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1843 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4872. Min Act: -0.1700

Data Index: 682676 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4721. Min Act: -0.1700

Data Index: 685973 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4536. Min Act: -0.1700

Data Index: 1166091 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4404. Min Act: -0.1700

Data Index: 274351 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4107. Min Act: -0.1700

Data Index: 935328 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4099. Min Act: -0.1700

Data Index: 1022895 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4051. Min Act: -0.1700

Data Index: 545058 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.4050. Min Act: -0.1700

Data Index: 303042 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3880. Min Act: -0.1700

Data Index: 374494 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3775. Min Act: -0.1700

Data Index: 1068482 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3700. Min Act: -0.1700

Data Index: 1081167 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3746. Min Act: -0.1700

Data Index: 69984 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3775. Min Act: -0.1700

Data Index: 55214 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3877. Min Act: -0.1700

Data Index: 699538 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3630. Min Act: -0.1700

Data Index: 366746 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3601. Min Act: -0.1700

Data Index: 1163604 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3620. Min Act: -0.1700

Data Index: 137911 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3629. Min Act: -0.1700

Data Index: 345678 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3584. Min Act: -0.1700

Data Index: 1116232 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 3.4872. Min Range: -3.4872

Max Act: 3.3587. Min Act: -0.1700

Data Index: 1074129 (C4 (Web Text))

Max Activating Token Index: 885