Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1920 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0726. Min Range: -3.0726

Max Act: 3.0726. Min Act: -0.1700

Data Index: 1340191 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 3.0726. Min Range: -3.0726

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1039746 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 3.0726. Min Range: -3.0726

Max Act: 3.0287. Min Act: -0.1700

Data Index: 589587 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 3.0726. Min Range: -3.0726

Max Act: 3.0090. Min Act: -0.1700

Data Index: 1257408 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.0726. Min Range: -3.0726

Max Act: 3.0092. Min Act: -0.1700

Data Index: 1057134 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9610. Min Act: -0.1700

Data Index: 338456 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9727. Min Act: -0.1700

Data Index: 335168 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9922. Min Act: -0.1700

Data Index: 166128 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9740. Min Act: -0.1700

Data Index: 1590990 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9608. Min Act: -0.1700

Data Index: 48129 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9487. Min Act: -0.1700

Data Index: 430259 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9345. Min Act: -0.1700

Data Index: 12527 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9429. Min Act: -0.1700

Data Index: 59748 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9459. Min Act: -0.1700

Data Index: 1083594 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9370. Min Act: -0.1700

Data Index: 1068530 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9457. Min Act: -0.1700

Data Index: 120335 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9337. Min Act: -0.1700

Data Index: 882968 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9257. Min Act: -0.1700

Data Index: 794694 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9183. Min Act: -0.1700

Data Index: 513953 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.0726. Min Range: -3.0726

Max Act: 2.9141. Min Act: -0.1700

Data Index: 739362 (C4 (Web Text))

Max Activating Token Index: 195