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

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

Neuron 2039 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: 3.8823. Min Range: -3.8823

Max Act: 3.8823. Min Act: -0.1700

Data Index: 826232 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7597. Min Act: -0.1700

Data Index: 167229 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7655. Min Act: -0.1700

Data Index: 1519305 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7423. Min Act: -0.1700

Data Index: 379561 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7183. Min Act: -0.1700

Data Index: 921461 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6898. Min Act: -0.1700

Data Index: 1186855 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6574. Min Act: -0.1700

Data Index: 977995 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6887. Min Act: -0.1700

Data Index: 259629 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6825. Min Act: -0.1700

Data Index: 762390 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6619. Min Act: -0.1700

Data Index: 248017 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6517. Min Act: -0.1700

Data Index: 916679 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6780. Min Act: -0.1700

Data Index: 1073971 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6318. Min Act: -0.1700

Data Index: 937442 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6341. Min Act: -0.1700

Data Index: 1301456 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6302. Min Act: -0.1700

Data Index: 42761 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6295. Min Act: -0.1700

Data Index: 589131 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6195. Min Act: -0.1700

Data Index: 390623 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6521. Min Act: -0.1700

Data Index: 540140 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6389. Min Act: -0.1700

Data Index: 1187241 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6169. Min Act: -0.1700

Data Index: 947750 (C4 (Web Text))

Max Activating Token Index: 218