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

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

Neuron 1052 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: 3.5246. Min Range: -3.5246

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1131720 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.5090. Min Act: -0.1700

Data Index: 1287067 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4463. Min Act: -0.1700

Data Index: 38290 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1215438 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4149. Min Act: -0.1700

Data Index: 546979 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4933. Min Act: -0.1700

Data Index: 643137 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4149. Min Act: -0.1700

Data Index: 1297175 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4463. Min Act: -0.1700

Data Index: 242111 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4619. Min Act: -0.1700

Data Index: 728202 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3835. Min Act: -0.1700

Data Index: 181796 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3835. Min Act: -0.1700

Data Index: 1305775 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3992. Min Act: -0.1700

Data Index: 876201 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3835. Min Act: -0.1700

Data Index: 4723 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3522. Min Act: -0.1700

Data Index: 843886 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3678. Min Act: -0.1700

Data Index: 490578 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3522. Min Act: -0.1700

Data Index: 482775 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3208. Min Act: -0.1700

Data Index: 41996 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3365. Min Act: -0.1700

Data Index: 894770 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3051. Min Act: -0.1700

Data Index: 1313952 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3365. Min Act: -0.1700

Data Index: 1149300 (C4 (Web Text))

Max Activating Token Index: 53