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

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

Neuron 502 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: 3.7630. Min Range: -3.7630

Max Act: 3.7630. Min Act: -0.1700

Data Index: 732712 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.6624. Min Act: -0.1700

Data Index: 12017 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.6607. Min Act: -0.1700

Data Index: 784483 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.6307. Min Act: -0.1700

Data Index: 1125428 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.6209. Min Act: -0.1700

Data Index: 987701 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.6124. Min Act: -0.1700

Data Index: 562129 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5905. Min Act: -0.1700

Data Index: 161668 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5622. Min Act: -0.1700

Data Index: 634566 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5378. Min Act: -0.1700

Data Index: 237223 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5643. Min Act: -0.1700

Data Index: 183615 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5334. Min Act: -0.1700

Data Index: 522766 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5201. Min Act: -0.1700

Data Index: 971128 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5234. Min Act: -0.1700

Data Index: 389057 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5202. Min Act: -0.1700

Data Index: 540229 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5044. Min Act: -0.1700

Data Index: 489452 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5147. Min Act: -0.1700

Data Index: 876144 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5334. Min Act: -0.1700

Data Index: 1082995 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.5192. Min Act: -0.1700

Data Index: 1359841 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.4897. Min Act: -0.1700

Data Index: 640822 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 3.7630. Min Range: -3.7630

Max Act: 3.4992. Min Act: -0.1700

Data Index: 1307556 (C4 (Web Text))

Max Activating Token Index: 49