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

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

Neuron 1884 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: 3.4907. Min Range: -3.4907

Max Act: 3.4907. Min Act: -0.1700

Data Index: 556494 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3915. Min Act: -0.1700

Data Index: 924906 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.4100. Min Act: -0.1700

Data Index: 216420 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3908. Min Act: -0.1700

Data Index: 897014 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3767. Min Act: -0.1700

Data Index: 727937 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3720. Min Act: -0.1700

Data Index: 182810 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3682. Min Act: -0.1700

Data Index: 1010103 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3485. Min Act: -0.1700

Data Index: 132144 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3239. Min Act: -0.1700

Data Index: 609467 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3309. Min Act: -0.1700

Data Index: 513649 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3064. Min Act: -0.1700

Data Index: 873611 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3162. Min Act: -0.1700

Data Index: 329411 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3377. Min Act: -0.1700

Data Index: 622484 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3311. Min Act: -0.1700

Data Index: 411045 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.3429. Min Act: -0.1700

Data Index: 964974 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1604856 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2883. Min Act: -0.1700

Data Index: 726674 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2676. Min Act: -0.1700

Data Index: 839747 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2704. Min Act: -0.1700

Data Index: 134503 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 3.4907. Min Range: -3.4907

Max Act: 3.2741. Min Act: -0.1700

Data Index: 252943 (C4 (Web Text))

Max Activating Token Index: 1005