Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.1270. Min Range: -7.1270

Max Act: 7.1270. Min Act: -0.1700

Data Index: 62673 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.9708. Min Act: -0.1700

Data Index: 183975 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.8145. Min Act: -0.1700

Data Index: 1141219 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.8770. Min Act: -0.1700

Data Index: 1144525 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.8458. Min Act: -0.1700

Data Index: 543559 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5958. Min Act: -0.1700

Data Index: 629436 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.6583. Min Act: -0.1700

Data Index: 884601 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.6583. Min Act: -0.1700

Data Index: 1170743 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.6583. Min Act: -0.1700

Data Index: 272006 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5645. Min Act: -0.1700

Data Index: 907928 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.6583. Min Act: -0.1700

Data Index: 442562 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5333. Min Act: -0.1700

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5645. Min Act: -0.1700

Data Index: 25461 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5020. Min Act: -0.1700

Data Index: 892892 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5020. Min Act: -0.1700

Data Index: 404710 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.4708. Min Act: -0.1700

Data Index: 1080579 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5020. Min Act: -0.1700

Data Index: 456467 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.5020. Min Act: -0.1700

Data Index: 477543 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.4708. Min Act: -0.1700

Data Index: 1284512 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 7.1270. Min Range: -7.1270

Max Act: 6.4395. Min Act: -0.1700

Data Index: 279725 (C4 (Web Text))

Max Activating Token Index: 149