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

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

Neuron 1902 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: 3.0306. Min Range: -3.0306

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1007145 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.9311. Min Act: -0.1697

Data Index: 661993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8798. Min Act: -0.1700

Data Index: 857839 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8979. Min Act: -0.1700

Data Index: 84488 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8780. Min Act: -0.1700

Data Index: 725355 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8700. Min Act: -0.1700

Data Index: 226664 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.9047. Min Act: -0.1700

Data Index: 66982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8373. Min Act: -0.1700

Data Index: 197656 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8602. Min Act: -0.1700

Data Index: 314687 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8573. Min Act: -0.1672

Data Index: 806729 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8654. Min Act: -0.1700

Data Index: 514762 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8757. Min Act: -0.1630

Data Index: 516135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8514. Min Act: -0.1700

Data Index: 615354 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8621. Min Act: -0.1700

Data Index: 668082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8662. Min Act: -0.1700

Data Index: 834117 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8493. Min Act: -0.1700

Data Index: 1253219 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8246. Min Act: -0.1671

Data Index: 67128 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8285. Min Act: -0.1700

Data Index: 944042 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8184. Min Act: -0.1690

Data Index: 1206304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.0306. Min Range: -3.0306

Max Act: 2.8103. Min Act: -0.1700

Data Index: 479770 (C4 (Web Text))

Max Activating Token Index: 1023