Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.6206. Min Act: -0.1700

Data Index: 1014599 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.5736. Min Act: -0.1700

Data Index: 730437 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.5423. Min Act: -0.1700

Data Index: 1159245 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.4326. Min Act: -0.1700

Data Index: 1273150 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.4012. Min Act: -0.1700

Data Index: 529216 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.4326. Min Act: -0.1700

Data Index: 655104 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3227. Min Act: -0.1700

Data Index: 834306 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3384. Min Act: -0.1700

Data Index: 576259 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3070. Min Act: -0.1700

Data Index: 1217260 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3384. Min Act: -0.1700

Data Index: 690881 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3227. Min Act: -0.1700

Data Index: 920180 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3227. Min Act: -0.1700

Data Index: 520749 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2599. Min Act: -0.1700

Data Index: 303254 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2599. Min Act: -0.1700

Data Index: 348778 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2442. Min Act: -0.1700

Data Index: 678157 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3070. Min Act: -0.1700

Data Index: 494473 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.3227. Min Act: -0.1700

Data Index: 429209 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2599. Min Act: -0.1700

Data Index: 394505 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2442. Min Act: -0.1700

Data Index: 527699 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.6206. Min Range: -3.6206

Max Act: 3.2442. Min Act: -0.1700

Data Index: 403859 (C4 (Web Text))

Max Activating Token Index: 27