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

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

Neuron 660 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: 3.6039. Min Range: -3.6039

Max Act: 3.5788. Min Act: -0.1700

Data Index: 751750 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.6039. Min Act: -0.1700

Data Index: 584059 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4958. Min Act: -0.1700

Data Index: 517247 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4863. Min Act: -0.1700

Data Index: 464106 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4942. Min Act: -0.1700

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4830. Min Act: -0.1700

Data Index: 1082433 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1159727 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4314. Min Act: -0.1700

Data Index: 1314791 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4607. Min Act: -0.1700

Data Index: 657374 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4088. Min Act: -0.1700

Data Index: 834001 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.4136. Min Act: -0.1700

Data Index: 1267418 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3912. Min Act: -0.1700

Data Index: 1151799 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3974. Min Act: -0.1700

Data Index: 550839 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3687. Min Act: -0.1700

Data Index: 750369 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3590. Min Act: -0.1700

Data Index: 1218198 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3768. Min Act: -0.1700

Data Index: 295860 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3669. Min Act: -0.1700

Data Index: 1096725 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3451. Min Act: -0.1700

Data Index: 479083 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3582. Min Act: -0.1700

Data Index: 434738 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 3.6039. Min Range: -3.6039

Max Act: 3.3490. Min Act: -0.1700

Data Index: 669982 (C4 (Web Text))

Max Activating Token Index: 367