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

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

Neuron 1654 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: 3.9835. Min Range: -3.9835

Max Act: 3.9835. Min Act: -0.1700

Data Index: 618061 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.8909. Min Act: -0.1700

Data Index: 973045 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.8775. Min Act: -0.1700

Data Index: 1206530 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7801. Min Act: -0.1700

Data Index: 157128 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7544. Min Act: -0.1700

Data Index: 330275 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7789. Min Act: -0.1700

Data Index: 248262 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7711. Min Act: -0.1700

Data Index: 140448 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7590. Min Act: -0.1700

Data Index: 1112071 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7106. Min Act: -0.1700

Data Index: 151871 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6907. Min Act: -0.1700

Data Index: 620638 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7028. Min Act: -0.1700

Data Index: 522472 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7110. Min Act: -0.1700

Data Index: 8894 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7020. Min Act: -0.1700

Data Index: 1091390 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7135. Min Act: -0.1700

Data Index: 1115283 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.7056. Min Act: -0.1700

Data Index: 704152 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6579. Min Act: -0.1700

Data Index: 1570560 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6863. Min Act: -0.1700

Data Index: 1510459 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6793. Min Act: -0.1700

Data Index: 262411 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6596. Min Act: -0.1700

Data Index: 969767 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 3.9835. Min Range: -3.9835

Max Act: 3.6876. Min Act: -0.1700

Data Index: 104675 (C4 (Web Text))

Max Activating Token Index: 480