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

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

Neuron 979 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: 4.5963. Min Range: -4.5963

Max Act: 4.5963. Min Act: -0.1700

Data Index: 501519 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4546. Min Act: -0.1700

Data Index: 452300 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4462. Min Act: -0.1700

Data Index: 331293 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4471. Min Act: -0.1700

Data Index: 1106390 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4303. Min Act: -0.1700

Data Index: 355277 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4197. Min Act: -0.1700

Data Index: 398562 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4203. Min Act: -0.1700

Data Index: 412488 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4513. Min Act: -0.1700

Data Index: 829617 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4230. Min Act: -0.1700

Data Index: 876429 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3893. Min Act: -0.1700

Data Index: 686890 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4033. Min Act: -0.1700

Data Index: 861839 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4097. Min Act: -0.1700

Data Index: 897781 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3922. Min Act: -0.1700

Data Index: 56888 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4003. Min Act: -0.1700

Data Index: 92832 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.4107. Min Act: -0.1700

Data Index: 1292471 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3581. Min Act: -0.1700

Data Index: 1051798 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3754. Min Act: -0.1700

Data Index: 474162 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3937. Min Act: -0.1700

Data Index: 27740 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3473. Min Act: -0.1700

Data Index: 418872 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 4.5963. Min Range: -4.5963

Max Act: 4.3829. Min Act: -0.1700

Data Index: 23892 (C4 (Web Text))

Max Activating Token Index: 749