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

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

Neuron 792 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: 3.0580. Min Range: -3.0580

Max Act: 3.0580. Min Act: -0.1700

Data Index: 190439 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9725. Min Act: -0.1700

Data Index: 1609831 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9897. Min Act: -0.1700

Data Index: 1373666 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8880. Min Act: -0.1700

Data Index: 1593687 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8789. Min Act: -0.1700

Data Index: 1611235 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8781. Min Act: -0.1700

Data Index: 90835 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8767. Min Act: -0.1700

Data Index: 1542121 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8854. Min Act: -0.1700

Data Index: 1363997 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8784. Min Act: -0.1700

Data Index: 1150042 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8726. Min Act: -0.1700

Data Index: 422866 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8409. Min Act: -0.1700

Data Index: 1599460 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8253. Min Act: -0.1700

Data Index: 1553980 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8154. Min Act: -0.1700

Data Index: 1229169 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8040. Min Act: -0.1700

Data Index: 1436699 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8003. Min Act: -0.1700

Data Index: 1269299 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8031. Min Act: -0.1700

Data Index: 1627154 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8024. Min Act: -0.1700

Data Index: 1380150 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8041. Min Act: -0.1700

Data Index: 19449 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8063. Min Act: -0.1700

Data Index: 762037 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.7956. Min Act: -0.1700

Data Index: 683612 (C4 (Web Text))

Max Activating Token Index: 279