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

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

Neuron 2045 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: 3.1459. Min Range: -3.1459

Max Act: 3.1440. Min Act: -0.1700

Data Index: 289697 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.1363. Min Act: -0.1700

Data Index: 553117 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.1459. Min Act: -0.1700

Data Index: 202811 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.1297. Min Act: -0.1700

Data Index: 589148 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0831. Min Act: -0.1700

Data Index: 217013 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0806. Min Act: -0.1700

Data Index: 308398 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0547. Min Act: -0.1700

Data Index: 8270 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0340. Min Act: -0.1700

Data Index: 682108 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0318. Min Act: -0.1700

Data Index: 783486 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0299. Min Act: -0.1700

Data Index: 764004 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0142. Min Act: -0.1700

Data Index: 978710 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9965. Min Act: -0.1700

Data Index: 746065 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9978. Min Act: -0.1700

Data Index: 355667 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9914. Min Act: -0.1700

Data Index: 558377 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9833. Min Act: -0.1700

Data Index: 1587524 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9793. Min Act: -0.1700

Data Index: 732286 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9882. Min Act: -0.1700

Data Index: 705394 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9607. Min Act: -0.1700

Data Index: 224429 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 3.1459. Min Range: -3.1459

Max Act: 2.9665. Min Act: -0.1700

Data Index: 85010 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 3.1459. Min Range: -3.1459

Max Act: 3.0030. Min Act: -0.1700

Data Index: 681778 (C4 (Web Text))

Max Activating Token Index: 954