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

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

Neuron 1113 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.6429. Min Act: -0.1700

Data Index: 934419 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.5802. Min Act: -0.1700

Data Index: 1093961 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.6116. Min Act: -0.1698

Data Index: 1245211 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.5489. Min Act: -0.1700

Data Index: 1383028 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1694

Data Index: 1224256 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.5489. Min Act: -0.1700

Data Index: 1098284 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.5176. Min Act: -0.1700

Data Index: 1020569 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 787391 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 10189 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 276420 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 591295 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 600498 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4862. Min Act: -0.1700

Data Index: 868810 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4549. Min Act: -0.1700

Data Index: 1056092 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4235. Min Act: -0.1700

Data Index: 1572017 (Python Code)

Max Activating Token Index: 547

Text #15

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4235. Min Act: -0.1700

Data Index: 50693 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4235. Min Act: -0.1700

Data Index: 527294 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.4549. Min Act: -0.1700

Data Index: 847471 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.3922. Min Act: -0.1700

Data Index: 707578 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.6429. Min Range: -3.6429

Max Act: 3.3608. Min Act: -0.1700

Data Index: 1394942 (Python Code)

Max Activating Token Index: 225