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

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

Neuron 1696 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.5823. Min Act: -0.1700

Data Index: 24818 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.5197. Min Act: -0.1700

Data Index: 1028932 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4883. Min Act: -0.1700

Data Index: 996782 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4883. Min Act: -0.1700

Data Index: 8643 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1191216 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4256. Min Act: -0.1700

Data Index: 913664 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4099. Min Act: -0.1700

Data Index: 469924 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4256. Min Act: -0.1700

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4099. Min Act: -0.1700

Data Index: 906886 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3943. Min Act: -0.1700

Data Index: 288214 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3786. Min Act: -0.1700

Data Index: 6382 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4099. Min Act: -0.1700

Data Index: 900372 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4099. Min Act: -0.1700

Data Index: 921984 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3629. Min Act: -0.1700

Data Index: 1067119 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3786. Min Act: -0.1700

Data Index: 382803 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3786. Min Act: -0.1700

Data Index: 1092108 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3786. Min Act: -0.1700

Data Index: 413584 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3158. Min Act: -0.1700

Data Index: 833293 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3786. Min Act: -0.1700

Data Index: 718114 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3158. Min Act: -0.1700

Data Index: 199091 (C4 (Web Text))

Max Activating Token Index: 22