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

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

Neuron 133 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: 3.9951. Min Range: -3.9951

Max Act: 3.9951. Min Act: -0.1700

Data Index: 197366 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.9638. Min Act: -0.1700

Data Index: 353550 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.9013. Min Act: -0.1700

Data Index: 1079383 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.9013. Min Act: -0.1700

Data Index: 1115187 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8388. Min Act: -0.1700

Data Index: 114710 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8388. Min Act: -0.1700

Data Index: 918345 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8075. Min Act: -0.1700

Data Index: 136239 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8075. Min Act: -0.1700

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8075. Min Act: -0.1700

Data Index: 894952 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8075. Min Act: -0.1700

Data Index: 293222 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.8075. Min Act: -0.1700

Data Index: 286208 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7449. Min Act: -0.1700

Data Index: 1110727 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7762. Min Act: -0.1700

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7449. Min Act: -0.1700

Data Index: 83250 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7293. Min Act: -0.1700

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7293. Min Act: -0.1700

Data Index: 679520 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7293. Min Act: -0.1700

Data Index: 133014 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7449. Min Act: -0.1700

Data Index: 562545 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7293. Min Act: -0.1700

Data Index: 916356 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.9951. Min Range: -3.9951

Max Act: 3.7293. Min Act: -0.1700

Data Index: 596080 (C4 (Web Text))

Max Activating Token Index: 819