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

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

Neuron 1481 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: 4.2347. Min Range: -4.2347

Max Act: 4.2347. Min Act: -0.1700

Data Index: 946727 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1409. Min Act: -0.1700

Data Index: 1188400 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1096. Min Act: -0.1700

Data Index: 1521481 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1096. Min Act: -0.1700

Data Index: 1574691 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1096. Min Act: -0.1700

Data Index: 1629100 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.0784. Min Act: -0.1700

Data Index: 539787 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1096. Min Act: -0.1700

Data Index: 968867 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.1096. Min Act: -0.1700

Data Index: 1533313 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.0471. Min Act: -0.1700

Data Index: 1570125 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.0471. Min Act: -0.1700

Data Index: 1391007 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.0471. Min Act: -0.1700

Data Index: 1367278 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 4.2347. Min Range: -4.2347

Max Act: 4.0471. Min Act: -0.1700

Data Index: 1598345 (Python Code)

Max Activating Token Index: 262

Text #12

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1510237 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9533. Min Act: -0.1700

Data Index: 1461157 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9846. Min Act: -0.1700

Data Index: 1635182 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1160128 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.8908. Min Act: -0.1700

Data Index: 1612330 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1522284 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9533. Min Act: -0.1700

Data Index: 1427861 (Python Code)

Max Activating Token Index: 946

Text #19

Max Range: 4.2347. Min Range: -4.2347

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1455140 (Python Code)

Max Activating Token Index: 485