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

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

Neuron 1788 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: 4.7083. Min Range: -4.7083

Max Act: 4.7083. Min Act: -0.1700

Data Index: 43630 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.4895. Min Act: -0.1700

Data Index: 569420 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.4270. Min Act: -0.1700

Data Index: 1082916 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.4270. Min Act: -0.1700

Data Index: 762505 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.3645. Min Act: -0.1700

Data Index: 325582 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.3645. Min Act: -0.1700

Data Index: 776783 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.3958. Min Act: -0.1700

Data Index: 1060405 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.3020. Min Act: -0.1700

Data Index: 787551 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2395. Min Act: -0.1700

Data Index: 983301 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2708. Min Act: -0.1700

Data Index: 427240 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2708. Min Act: -0.1700

Data Index: 350208 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2708. Min Act: -0.1700

Data Index: 1147692 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.3020. Min Act: -0.1700

Data Index: 953117 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2083. Min Act: -0.1700

Data Index: 707166 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2083. Min Act: -0.1700

Data Index: 242021 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2395. Min Act: -0.1700

Data Index: 1250993 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2708. Min Act: -0.1700

Data Index: 61014 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2395. Min Act: -0.1700

Data Index: 9569 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.1457. Min Act: -0.1700

Data Index: 1554541 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 4.7083. Min Range: -4.7083

Max Act: 4.2083. Min Act: -0.1700

Data Index: 917559 (C4 (Web Text))

Max Activating Token Index: 540