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

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

Neuron 1661 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: 3.9093. Min Range: -3.9093

Max Act: 3.9082. Min Act: -0.1700

Data Index: 1248414 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.9093. Min Act: -0.1700

Data Index: 940110 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.9028. Min Act: -0.1700

Data Index: 1238535 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8708. Min Act: -0.1700

Data Index: 272820 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8655. Min Act: -0.1700

Data Index: 1170990 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8724. Min Act: -0.1700

Data Index: 914030 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8508. Min Act: -0.1700

Data Index: 1351131 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8535. Min Act: -0.1700

Data Index: 316025 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8567. Min Act: -0.1700

Data Index: 946414 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8262. Min Act: -0.1700

Data Index: 1143999 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8149. Min Act: -0.1700

Data Index: 289212 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8068. Min Act: -0.1700

Data Index: 772774 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8050. Min Act: -0.1700

Data Index: 501285 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7991. Min Act: -0.1699

Data Index: 1039089 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.8114. Min Act: -0.1700

Data Index: 409843 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7819. Min Act: -0.1700

Data Index: 1276473 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7722. Min Act: -0.1700

Data Index: 188456 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1355321 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7656. Min Act: -0.1700

Data Index: 562485 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.9093. Min Range: -3.9093

Max Act: 3.7436. Min Act: -0.1700

Data Index: 329973 (C4 (Web Text))

Max Activating Token Index: 959