Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1026 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.8165. Min Act: -0.1700

Data Index: 593948 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7540. Min Act: -0.1700

Data Index: 818625 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7540. Min Act: -0.1700

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7540. Min Act: -0.1700

Data Index: 671687 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1017249 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1317340 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7227. Min Act: -0.1700

Data Index: 71374 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.7227. Min Act: -0.1700

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6601. Min Act: -0.1700

Data Index: 200940 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 735671 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6601. Min Act: -0.1700

Data Index: 764220 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6601. Min Act: -0.1700

Data Index: 478443 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6601. Min Act: -0.1700

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 663200 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 827772 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 880258 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 895980 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 420279 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6288. Min Act: -0.1700

Data Index: 382047 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6601. Min Act: -0.1700

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 467