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

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

Neuron 1908 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: 4.8119. Min Range: -4.8119

Max Act: 4.8119. Min Act: -0.1700

Data Index: 1349306 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.7207. Min Act: -0.1700

Data Index: 1215392 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.6566. Min Act: -0.1700

Data Index: 126485 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.6856. Min Act: -0.1700

Data Index: 913592 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.6089. Min Act: -0.1700

Data Index: 1139424 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.6187. Min Act: -0.1700

Data Index: 514729 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.6331. Min Act: -0.1700

Data Index: 1199344 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5761. Min Act: -0.1700

Data Index: 574950 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5723. Min Act: -0.1700

Data Index: 916178 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5402. Min Act: -0.1700

Data Index: 555191 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.4972. Min Act: -0.1700

Data Index: 381410 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5191. Min Act: -0.1700

Data Index: 464091 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5523. Min Act: -0.1700

Data Index: 800404 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5435. Min Act: -0.1700

Data Index: 471414 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5039. Min Act: -0.1700

Data Index: 7688 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.4956. Min Act: -0.1700

Data Index: 1095518 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.4904. Min Act: -0.1700

Data Index: 830202 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.5439. Min Act: -0.1700

Data Index: 509245 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.4944. Min Act: -0.1700

Data Index: 272821 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 4.8119. Min Range: -4.8119

Max Act: 4.4998. Min Act: -0.1700

Data Index: 967418 (C4 (Web Text))

Max Activating Token Index: 61