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

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

Neuron 1528 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: 2.9538. Min Range: -2.9538

Max Act: 2.9538. Min Act: -0.1700

Data Index: 320896 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.9379. Min Act: -0.1700

Data Index: 37414 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.9284. Min Act: -0.1700

Data Index: 241201 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.9246. Min Act: -0.1699

Data Index: 395271 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.9232. Min Act: -0.1700

Data Index: 44648 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.9032. Min Act: -0.1700

Data Index: 529944 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8971. Min Act: -0.1700

Data Index: 881745 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8678. Min Act: -0.1700

Data Index: 1170253 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8650. Min Act: -0.1700

Data Index: 740007 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8561. Min Act: -0.1700

Data Index: 534280 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8597. Min Act: -0.1700

Data Index: 647698 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8363. Min Act: -0.1700

Data Index: 415597 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8466. Min Act: -0.1700

Data Index: 976767 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8394. Min Act: -0.1700

Data Index: 1084314 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8422. Min Act: -0.1700

Data Index: 1235791 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8352. Min Act: -0.1700

Data Index: 614481 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8363. Min Act: -0.1700

Data Index: 326495 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8290. Min Act: -0.1698

Data Index: 584564 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8155. Min Act: -0.1700

Data Index: 889135 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 2.9538. Min Range: -2.9538

Max Act: 2.8238. Min Act: -0.1700

Data Index: 914588 (C4 (Web Text))

Max Activating Token Index: 22