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

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

Neuron 453 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: 3.3205. Min Range: -3.3205

Max Act: 3.3205. Min Act: -0.1700

Data Index: 1519594 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1728. Min Act: -0.1700

Data Index: 416985 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1136. Min Act: -0.1700

Data Index: 871202 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0748. Min Act: -0.1700

Data Index: 864599 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0952. Min Act: -0.1700

Data Index: 261355 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1188. Min Act: -0.1700

Data Index: 1143774 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0797. Min Act: -0.1700

Data Index: 54806 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0633. Min Act: -0.1700

Data Index: 867974 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0452. Min Act: -0.1700

Data Index: 249278 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0654. Min Act: -0.1700

Data Index: 850568 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0254. Min Act: -0.1699

Data Index: 419122 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1055626 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0415. Min Act: -0.1700

Data Index: 322973 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0286. Min Act: -0.1700

Data Index: 521389 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0447. Min Act: -0.1700

Data Index: 9810 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0185. Min Act: -0.1700

Data Index: 1084526 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0407. Min Act: -0.1700

Data Index: 1344590 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0494. Min Act: -0.1700

Data Index: 746302 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0292. Min Act: -0.1700

Data Index: 522413 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.0147. Min Act: -0.1700

Data Index: 465015 (C4 (Web Text))

Max Activating Token Index: 279