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

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

Neuron 1190 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: 3.2340. Min Range: -3.2340

Max Act: 3.2340. Min Act: -0.1700

Data Index: 177717 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.2183. Min Act: -0.1700

Data Index: 49009 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1396. Min Act: -0.1700

Data Index: 109039 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0134. Min Act: -0.1700

Data Index: 510157 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0134. Min Act: -0.1700

Data Index: 796579 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0134. Min Act: -0.1700

Data Index: 769347 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0134. Min Act: -0.1700

Data Index: 1169830 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0134. Min Act: -0.1700

Data Index: 174068 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9818. Min Act: -0.1700

Data Index: 650167 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9343. Min Act: -0.1700

Data Index: 65179 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9976. Min Act: -0.1700

Data Index: 1153745 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.8867. Min Act: -0.1700

Data Index: 1104706 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9185. Min Act: -0.1700

Data Index: 1106013 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9343. Min Act: -0.1700

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9501. Min Act: -0.1700

Data Index: 326333 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9343. Min Act: -0.1700

Data Index: 234795 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9343. Min Act: -0.1700

Data Index: 630676 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9185. Min Act: -0.1700

Data Index: 747681 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9026. Min Act: -0.1700

Data Index: 103095 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 3.2340. Min Range: -3.2340

Max Act: 2.9185. Min Act: -0.1700

Data Index: 810641 (C4 (Web Text))

Max Activating Token Index: 581