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

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

Neuron 1323 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: 2.9135. Min Range: -2.9135

Max Act: 2.9135. Min Act: -0.1700

Data Index: 1021975 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.8568. Min Act: -0.1700

Data Index: 538971 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.7471. Min Act: -0.1700

Data Index: 1304944 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.7357. Min Act: -0.1700

Data Index: 394533 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.7096. Min Act: -0.1700

Data Index: 254213 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1300004 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6561. Min Act: -0.1700

Data Index: 782988 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6821. Min Act: -0.1693

Data Index: 565935 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6898. Min Act: -0.1700

Data Index: 513361 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6771. Min Act: -0.1700

Data Index: 247745 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6581. Min Act: -0.1700

Data Index: 848490 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6691. Min Act: -0.1700

Data Index: 634145 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6420. Min Act: -0.1700

Data Index: 1016048 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6343. Min Act: -0.1700

Data Index: 512160 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6225. Min Act: -0.1700

Data Index: 1202624 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6656. Min Act: -0.1693

Data Index: 575862 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6287. Min Act: -0.1700

Data Index: 146457 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6335. Min Act: -0.1699

Data Index: 520432 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6502. Min Act: -0.1700

Data Index: 714379 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.9135. Min Range: -2.9135

Max Act: 2.6059. Min Act: -0.1700

Data Index: 8577 (C4 (Web Text))

Max Activating Token Index: 1012