Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 905 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.4137. Min Act: -0.1700

Data Index: 1050586 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3824. Min Act: -0.1700

Data Index: 98353 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3510. Min Act: -0.1700

Data Index: 467196 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3510. Min Act: -0.1700

Data Index: 422662 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.3039. Min Act: -0.1700

Data Index: 730517 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2882. Min Act: -0.1700

Data Index: 125056 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2096. Min Act: -0.1700

Data Index: 393173 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2253. Min Act: -0.1700

Data Index: 735753 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2253. Min Act: -0.1700

Data Index: 229714 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1939. Min Act: -0.1700

Data Index: 1042597 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.2096. Min Act: -0.1700

Data Index: 166067 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1939. Min Act: -0.1700

Data Index: 579670 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1781. Min Act: -0.1700

Data Index: 181490 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1624. Min Act: -0.1700

Data Index: 426005 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1624. Min Act: -0.1700

Data Index: 43200 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1466. Min Act: -0.1700

Data Index: 792102 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1624. Min Act: -0.1700

Data Index: 857576 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1781. Min Act: -0.1700

Data Index: 478239 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1309. Min Act: -0.1700

Data Index: 681208 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 3.4137. Min Range: -3.4137

Max Act: 3.1466. Min Act: -0.1700

Data Index: 114174 (C4 (Web Text))

Max Activating Token Index: 631