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

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

Neuron 1961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.5953. Min Act: -0.1700

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.5953. Min Act: -0.1700

Data Index: 484520 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.6265. Min Act: -0.1700

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.5953. Min Act: -0.1700

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4703. Min Act: -0.1700

Data Index: 169102 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.5015. Min Act: -0.1700

Data Index: 37435 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4703. Min Act: -0.1700

Data Index: 1232323 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.5015. Min Act: -0.1700

Data Index: 808013 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4390. Min Act: -0.1700

Data Index: 1165559 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4703. Min Act: -0.1700

Data Index: 24223 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4703. Min Act: -0.1700

Data Index: 973600 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4390. Min Act: -0.1700

Data Index: 1327979 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4390. Min Act: -0.1700

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3765. Min Act: -0.1700

Data Index: 1304226 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.4078. Min Act: -0.1700

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3765. Min Act: -0.1700

Data Index: 994233 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3453. Min Act: -0.1700

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3140. Min Act: -0.1700

Data Index: 362827 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3453. Min Act: -0.1700

Data Index: 579557 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.6265. Min Range: -5.6265

Max Act: 5.3140. Min Act: -0.1700

Data Index: 421527 (C4 (Web Text))

Max Activating Token Index: 257