Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4980. Min Act: -0.1700

Data Index: 1085131 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4510. Min Act: -0.1700

Data Index: 313811 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4196. Min Act: -0.1700

Data Index: 470886 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4039. Min Act: -0.1700

Data Index: 255934 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3883. Min Act: -0.1700

Data Index: 665121 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4039. Min Act: -0.1700

Data Index: 502458 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.4039. Min Act: -0.1700

Data Index: 523503 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3726. Min Act: -0.1700

Data Index: 251127 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3569. Min Act: -0.1700

Data Index: 397404 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3412. Min Act: -0.1700

Data Index: 441766 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1157082 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1206915 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2941. Min Act: -0.1700

Data Index: 678643 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2941. Min Act: -0.1700

Data Index: 8404 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.3569. Min Act: -0.1699

Data Index: 1045031 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2784. Min Act: -0.1700

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2941. Min Act: -0.1700

Data Index: 34750 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2941. Min Act: -0.1700

Data Index: 383798 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2784. Min Act: -0.1700

Data Index: 573203 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.4980. Min Range: -3.4980

Max Act: 3.2941. Min Act: -0.1700

Data Index: 631872 (C4 (Web Text))

Max Activating Token Index: 321