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

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

Neuron 1502 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: 3.9362. Min Range: -3.9362

Max Act: 3.9362. Min Act: -0.1700

Data Index: 85616 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.8395. Min Act: -0.1700

Data Index: 204551 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.6908. Min Act: -0.1696

Data Index: 616103 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.7217. Min Act: -0.1700

Data Index: 1147786 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.6735. Min Act: -0.1700

Data Index: 1251984 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.6381. Min Act: -0.1700

Data Index: 446587 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5761. Min Act: -0.1700

Data Index: 639205 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.6102. Min Act: -0.1700

Data Index: 405560 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5841. Min Act: -0.1700

Data Index: 577689 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5583. Min Act: -0.1700

Data Index: 524735 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5137. Min Act: -0.1700

Data Index: 1357014 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5163. Min Act: -0.1700

Data Index: 907812 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5125. Min Act: -0.1700

Data Index: 400209 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4905. Min Act: -0.1700

Data Index: 1289532 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4792. Min Act: -0.1700

Data Index: 1080719 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.5053. Min Act: -0.1699

Data Index: 141864 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4894. Min Act: -0.1700

Data Index: 1066676 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4598. Min Act: -0.1700

Data Index: 1318111 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4545. Min Act: -0.1699

Data Index: 293726 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 3.9362. Min Range: -3.9362

Max Act: 3.4144. Min Act: -0.1700

Data Index: 487824 (C4 (Web Text))

Max Activating Token Index: 827