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

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

Neuron 152 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.6587. Min Act: -0.1700

Data Index: 1045473 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.5178. Min Act: -0.1700

Data Index: 260667 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4864. Min Act: -0.1700

Data Index: 876310 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4864. Min Act: -0.1700

Data Index: 417202 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4708. Min Act: -0.1700

Data Index: 128116 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4551. Min Act: -0.1700

Data Index: 488953 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4394. Min Act: -0.1700

Data Index: 990264 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4081. Min Act: -0.1700

Data Index: 861045 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4237. Min Act: -0.1700

Data Index: 146121 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 571837 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 954872 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1173459 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 914884 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1160739 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3610. Min Act: -0.1700

Data Index: 589954 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 142322 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3767. Min Act: -0.1700

Data Index: 829114 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3453. Min Act: -0.1700

Data Index: 20873 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3610. Min Act: -0.1700

Data Index: 441703 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3453. Min Act: -0.1700

Data Index: 161188 (C4 (Web Text))

Max Activating Token Index: 183