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

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

Neuron 1212 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: 7.9719. Min Range: -7.9719

Max Act: 7.9719. Min Act: -0.1700

Data Index: 1072059 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.7315. Min Act: -0.1700

Data Index: 1161855 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.7041. Min Act: -0.1700

Data Index: 940516 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4795. Min Act: -0.1700

Data Index: 365882 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4988. Min Act: -0.1700

Data Index: 1123359 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4877. Min Act: -0.1700

Data Index: 621777 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4893. Min Act: -0.1700

Data Index: 1453046 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.5005. Min Act: -0.1700

Data Index: 349555 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.5186. Min Act: -0.1700

Data Index: 914769 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.5079. Min Act: -0.1700

Data Index: 676016 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3985. Min Act: -0.1700

Data Index: 1155802 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4318. Min Act: -0.1700

Data Index: 1367750 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3333. Min Act: -0.1700

Data Index: 317765 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3727. Min Act: -0.1700

Data Index: 1013232 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.4153. Min Act: -0.1700

Data Index: 1571884 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3507. Min Act: -0.1700

Data Index: 1483198 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3400. Min Act: -0.1700

Data Index: 442960 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3388. Min Act: -0.1700

Data Index: 1214980 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.3019. Min Act: -0.1700

Data Index: 967025 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 7.9719. Min Range: -7.9719

Max Act: 7.2385. Min Act: -0.1700

Data Index: 205064 (C4 (Web Text))

Max Activating Token Index: 257