Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.6323. Min Act: -0.1700

Data Index: 484390 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.6011. Min Act: -0.1700

Data Index: 1229518 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.6011. Min Act: -0.1700

Data Index: 4939 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.5386. Min Act: -0.1700

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3823. Min Act: -0.1700

Data Index: 766569 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.2886. Min Act: -0.1700

Data Index: 140500 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 302934 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.5073. Min Act: -0.1700

Data Index: 169989 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4136. Min Act: -0.1700

Data Index: 842035 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.2573. Min Act: -0.1700

Data Index: 41144 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 1320220 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3823. Min Act: -0.1700

Data Index: 529086 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3511. Min Act: -0.1700

Data Index: 527096 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3823. Min Act: -0.1700

Data Index: 955928 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 112600 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3511. Min Act: -0.1700

Data Index: 1064058 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4136. Min Act: -0.1700

Data Index: 698895 (C4 (Web Text))

Max Activating Token Index: 895