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

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

Neuron 1606 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: 4.3240. Min Range: -4.3240

Max Act: 4.3240. Min Act: -0.1700

Data Index: 413354 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 4.3240. Min Range: -4.3240

Max Act: 4.0427. Min Act: -0.1700

Data Index: 334349 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 4.3240. Min Range: -4.3240

Max Act: 4.0114. Min Act: -0.1700

Data Index: 115103 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.3240. Min Range: -4.3240

Max Act: 4.0114. Min Act: -0.1700

Data Index: 795746 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9801. Min Act: -0.1700

Data Index: 1258075 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9645. Min Act: -0.1700

Data Index: 790573 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9489. Min Act: -0.1700

Data Index: 321124 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9801. Min Act: -0.1700

Data Index: 461308 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9645. Min Act: -0.1700

Data Index: 130787 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9801. Min Act: -0.1700

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9489. Min Act: -0.1700

Data Index: 588970 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9645. Min Act: -0.1700

Data Index: 233111 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.8863. Min Act: -0.1700

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9332. Min Act: -0.1700

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9489. Min Act: -0.1700

Data Index: 141212 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9801. Min Act: -0.1700

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9489. Min Act: -0.1700

Data Index: 630408 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9645. Min Act: -0.1700

Data Index: 47863 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9645. Min Act: -0.1700

Data Index: 656323 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 4.3240. Min Range: -4.3240

Max Act: 3.9489. Min Act: -0.1700

Data Index: 1125538 (C4 (Web Text))

Max Activating Token Index: 71