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

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

Neuron 1531 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: 5.4685. Min Range: -5.4685

Max Act: 5.4685. Min Act: -0.1700

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.4373. Min Act: -0.1700

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.4373. Min Act: -0.1700

Data Index: 294565 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.4373. Min Act: -0.1700

Data Index: 863802 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3435. Min Act: -0.1700

Data Index: 95223 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3748. Min Act: -0.1700

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3748. Min Act: -0.1700

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3435. Min Act: -0.1700

Data Index: 1293312 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3123. Min Act: -0.1700

Data Index: 1006212 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1700

Data Index: 9083 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1700

Data Index: 382941 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1700

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3123. Min Act: -0.1699

Data Index: 1023594 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1698

Data Index: 1137494 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1699

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2810. Min Act: -0.1700

Data Index: 1242800 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.3123. Min Act: -0.1695

Data Index: 144414 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2498. Min Act: -0.1700

Data Index: 763549 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 5.4685. Min Range: -5.4685

Max Act: 5.2498. Min Act: -0.1699

Data Index: 689302 (C4 (Web Text))

Max Activating Token Index: 231