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

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

Neuron 1696 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: 5.6633. Min Range: -5.6633

Max Act: 5.6633. Min Act: -0.1700

Data Index: 393443 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.5383. Min Act: -0.1700

Data Index: 1007358 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.5383. Min Act: -0.1700

Data Index: 2652 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4758. Min Act: -0.1700

Data Index: 79075 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4758. Min Act: -0.1700

Data Index: 837179 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.5070. Min Act: -0.1700

Data Index: 361245 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.5070. Min Act: -0.1700

Data Index: 520239 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 1236791 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4758. Min Act: -0.1700

Data Index: 1301839 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 240369 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 271255 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 495489 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4758. Min Act: -0.1700

Data Index: 319469 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 281469 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4445. Min Act: -0.1700

Data Index: 251168 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.3820. Min Act: -0.1700

Data Index: 924156 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4133. Min Act: -0.1700

Data Index: 1013166 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.4133. Min Act: -0.1700

Data Index: 1107565 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.3820. Min Act: -0.1700

Data Index: 1197551 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 5.6633. Min Range: -5.6633

Max Act: 5.3820. Min Act: -0.1700

Data Index: 1305000 (C4 (Web Text))

Max Activating Token Index: 705