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

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

Neuron 68 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: 3.6518. Min Range: -3.6518

Max Act: 3.6518. Min Act: -0.1700

Data Index: 1054983 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4738. Min Act: -0.1700

Data Index: 229411 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4060. Min Act: -0.1700

Data Index: 563975 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3444. Min Act: -0.1700

Data Index: 882483 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3479. Min Act: -0.1700

Data Index: 63742 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3505. Min Act: -0.1700

Data Index: 802862 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3603. Min Act: -0.1700

Data Index: 588668 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1166094 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3064. Min Act: -0.1700

Data Index: 233512 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.3069. Min Act: -0.1700

Data Index: 800586 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1088634 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2888. Min Act: -0.1700

Data Index: 657523 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2564. Min Act: -0.1700

Data Index: 812851 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2584. Min Act: -0.1700

Data Index: 927049 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2659. Min Act: -0.1700

Data Index: 279586 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2528. Min Act: -0.1700

Data Index: 282347 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2506. Min Act: -0.1700

Data Index: 242041 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2496. Min Act: -0.1700

Data Index: 290235 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2614. Min Act: -0.1700

Data Index: 789628 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.2696. Min Act: -0.1700

Data Index: 601705 (C4 (Web Text))

Max Activating Token Index: 915