Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1793 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.6757. Min Act: -0.1700

Data Index: 1147376 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5817. Min Act: -0.1700

Data Index: 793918 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5817. Min Act: -0.1700

Data Index: 953800 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5504. Min Act: -0.1700

Data Index: 193628 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 804839 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 454545 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 791812 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 46581 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 1199143 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 27250 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1028638 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 607182 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 1112540 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 406391 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.5191. Min Act: -0.1700

Data Index: 885719 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 803560 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 474480 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 468440 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1079711 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.6757. Min Range: -3.6757

Max Act: 3.4877. Min Act: -0.1700

Data Index: 741297 (C4 (Web Text))

Max Activating Token Index: 177