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

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

Neuron 1449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.4050. Min Act: -0.1700

Data Index: 1420497 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3579. Min Act: -0.1700

Data Index: 1366273 (Python Code)

Max Activating Token Index: 544

Text #2

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3422. Min Act: -0.1700

Data Index: 634323 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3422. Min Act: -0.1700

Data Index: 1427794 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3108. Min Act: -0.1700

Data Index: 1091371 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3108. Min Act: -0.1700

Data Index: 1642247 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2951. Min Act: -0.1700

Data Index: 1486644 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3265. Min Act: -0.1700

Data Index: 617161 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3108. Min Act: -0.1700

Data Index: 815075 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.3108. Min Act: -0.1700

Data Index: 1413352 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1637195 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2637. Min Act: -0.1700

Data Index: 1460680 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2951. Min Act: -0.1700

Data Index: 1319400 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2480. Min Act: -0.1700

Data Index: 400730 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2480. Min Act: -0.1700

Data Index: 220876 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1293020 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2480. Min Act: -0.1700

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2165. Min Act: -0.1700

Data Index: 1545099 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2165. Min Act: -0.1700

Data Index: 300606 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.4050. Min Range: -3.4050

Max Act: 3.2008. Min Act: -0.1700

Data Index: 1647030 (Python Code)

Max Activating Token Index: 820