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

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

Neuron 378 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: 3.5861. Min Range: -3.5861

Max Act: 3.5861. Min Act: -0.1700

Data Index: 1189347 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.5334. Min Act: -0.1700

Data Index: 366513 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.4918. Min Act: -0.1649

Data Index: 918276 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.4321. Min Act: -0.1700

Data Index: 912186 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3828. Min Act: -0.1700

Data Index: 1375214 (Python Code)

Max Activating Token Index: 856

Text #5

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3979. Min Act: -0.1700

Data Index: 1214391 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.4000. Min Act: -0.1700

Data Index: 502839 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3998. Min Act: -0.1700

Data Index: 711195 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3918. Min Act: -0.1700

Data Index: 415082 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3700. Min Act: -0.1700

Data Index: 302984 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1160102 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3689. Min Act: -0.1700

Data Index: 54227 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1646440 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3486. Min Act: -0.1700

Data Index: 1384772 (Python Code)

Max Activating Token Index: 660

Text #14

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3562. Min Act: -0.1700

Data Index: 1509713 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1415965 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3554. Min Act: -0.1700

Data Index: 521592 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3459. Min Act: -0.1700

Data Index: 667719 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3682. Min Act: -0.1700

Data Index: 1267900 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 3.5861. Min Range: -3.5861

Max Act: 3.3269. Min Act: -0.1700

Data Index: 801211 (C4 (Web Text))

Max Activating Token Index: 652