Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 211 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.3501. Min Range: -8.3501

Max Act: 8.3501. Min Act: -0.1700

Data Index: 1049264 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.9751. Min Act: -0.1700

Data Index: 367919 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.6314. Min Act: -0.1700

Data Index: 440698 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.5376. Min Act: -0.1700

Data Index: 57256 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.5376. Min Act: -0.1700

Data Index: 124280 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.4751. Min Act: -0.1700

Data Index: 273750 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.6001. Min Act: -0.1700

Data Index: 81449 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.4439. Min Act: -0.1700

Data Index: 1350365 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.5064. Min Act: -0.1700

Data Index: 251358 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.3501. Min Act: -0.1700

Data Index: 122164 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.4439. Min Act: -0.1700

Data Index: 986127 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.3501. Min Act: -0.1700

Data Index: 502591 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.3501. Min Act: -0.1700

Data Index: 752349 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.3501. Min Act: -0.1700

Data Index: 209481 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.2564. Min Act: -0.1700

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.1939. Min Act: -0.1700

Data Index: 1151601 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.2564. Min Act: -0.1700

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.2564. Min Act: -0.1700

Data Index: 1246975 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.1626. Min Act: -0.1700

Data Index: 38873 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 8.3501. Min Range: -8.3501

Max Act: 7.1939. Min Act: -0.1700

Data Index: 39680 (C4 (Web Text))

Max Activating Token Index: 872