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

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

Neuron 1031 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: 3.5476. Min Range: -3.5476

Max Act: 3.5476. Min Act: -0.1700

Data Index: 752507 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.5101. Min Act: -0.1700

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4884. Min Act: -0.1700

Data Index: 1051570 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4595. Min Act: -0.1700

Data Index: 871732 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4464. Min Act: -0.1700

Data Index: 106745 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4391. Min Act: -0.1700

Data Index: 210481 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4347. Min Act: -0.1700

Data Index: 699 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4327. Min Act: -0.1700

Data Index: 1159922 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4225. Min Act: -0.1700

Data Index: 153232 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4277. Min Act: -0.1700

Data Index: 596821 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4051. Min Act: -0.1700

Data Index: 979691 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4126. Min Act: -0.1700

Data Index: 1206061 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3963. Min Act: -0.1700

Data Index: 239215 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3964. Min Act: -0.1700

Data Index: 573883 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.4027. Min Act: -0.1700

Data Index: 1037756 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3847. Min Act: -0.1700

Data Index: 699673 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3852. Min Act: -0.1700

Data Index: 133886 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1162260 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3587. Min Act: -0.1700

Data Index: 743498 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.5476. Min Range: -3.5476

Max Act: 3.3716. Min Act: -0.1699

Data Index: 494874 (C4 (Web Text))

Max Activating Token Index: 5