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

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

Neuron 1505 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: 5.4544. Min Range: -5.4544

Max Act: 5.4544. Min Act: -0.1700

Data Index: 8256 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.3919. Min Act: -0.1700

Data Index: 212569 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2669. Min Act: -0.1700

Data Index: 176951 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2044. Min Act: -0.1700

Data Index: 85274 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2356. Min Act: -0.1700

Data Index: 4011 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2669. Min Act: -0.1700

Data Index: 611467 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.1731. Min Act: -0.1700

Data Index: 999547 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2044. Min Act: -0.1700

Data Index: 704085 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.1731. Min Act: -0.1700

Data Index: 727983 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.2044. Min Act: -0.1700

Data Index: 1234474 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.1419. Min Act: -0.1700

Data Index: 1010313 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.1106. Min Act: -0.1700

Data Index: 700101 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.1106. Min Act: -0.1700

Data Index: 257741 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0794. Min Act: -0.1700

Data Index: 718618 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0481. Min Act: -0.1700

Data Index: 301534 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0794. Min Act: -0.1700

Data Index: 523031 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0481. Min Act: -0.1700

Data Index: 936152 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0794. Min Act: -0.1700

Data Index: 937033 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0794. Min Act: -0.1700

Data Index: 187496 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 5.4544. Min Range: -5.4544

Max Act: 5.0169. Min Act: -0.1700

Data Index: 474410 (C4 (Web Text))

Max Activating Token Index: 268