Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 949 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.6454. Min Act: -0.1700

Data Index: 368986 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.6333. Min Act: -0.1700

Data Index: 128610 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.6036. Min Act: -0.1700

Data Index: 671887 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.5594. Min Act: -0.1700

Data Index: 531924 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.5533. Min Act: -0.1700

Data Index: 980227 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.5261. Min Act: -0.1700

Data Index: 1225005 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4966. Min Act: -0.1700

Data Index: 393630 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4841. Min Act: -0.1700

Data Index: 846052 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4614. Min Act: -0.1700

Data Index: 362596 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4277. Min Act: -0.1700

Data Index: 1057611 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4303. Min Act: -0.1700

Data Index: 1197028 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4292. Min Act: -0.1700

Data Index: 1013814 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4540. Min Act: -0.1700

Data Index: 88968 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4144. Min Act: -0.1700

Data Index: 422851 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4253. Min Act: -0.1700

Data Index: 456173 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4149. Min Act: -0.1700

Data Index: 733967 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4143. Min Act: -0.1700

Data Index: 828528 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.4157. Min Act: -0.1700

Data Index: 1140305 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.3924. Min Act: -0.1700

Data Index: 470859 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.3977. Min Act: -0.1700

Data Index: 601255 (C4 (Web Text))

Max Activating Token Index: 555