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

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

Neuron 834 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: 3.4486. Min Range: -3.4486

Max Act: 3.4486. Min Act: -0.1700

Data Index: 499880 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.4410. Min Act: -0.1700

Data Index: 1416137 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3946. Min Act: -0.1700

Data Index: 823844 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3949. Min Act: -0.1700

Data Index: 283194 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3934. Min Act: -0.1700

Data Index: 219074 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3778. Min Act: -0.1700

Data Index: 1192354 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3577. Min Act: -0.1700

Data Index: 1227051 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3693. Min Act: -0.1700

Data Index: 694310 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3691. Min Act: -0.1700

Data Index: 582104 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3670. Min Act: -0.1700

Data Index: 36887 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3427. Min Act: -0.1700

Data Index: 831383 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3205. Min Act: -0.1700

Data Index: 1632938 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3336. Min Act: -0.1699

Data Index: 1619601 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3083. Min Act: -0.1700

Data Index: 1468120 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3144. Min Act: -0.1700

Data Index: 1559167 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3090. Min Act: -0.1700

Data Index: 1079006 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3183. Min Act: -0.1700

Data Index: 119155 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1232207 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2887. Min Act: -0.1700

Data Index: 258255 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2757. Min Act: -0.1700

Data Index: 558668 (C4 (Web Text))

Max Activating Token Index: 37