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

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

Neuron 1021 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: 4.2939. Min Range: -4.2939

Max Act: 4.2939. Min Act: -0.1643

Data Index: 1409278 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.2124. Min Act: -0.1699

Data Index: 1575455 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1821. Min Act: -0.1700

Data Index: 831287 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1809. Min Act: -0.1680

Data Index: 1484964 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1002. Min Act: -0.1698

Data Index: 168889 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1191. Min Act: -0.1643

Data Index: 1473659 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1208. Min Act: -0.1700

Data Index: 1536158 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0817. Min Act: -0.1700

Data Index: 1649764 (Python Code)

Max Activating Token Index: 464

Text #8

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1044. Min Act: -0.1700

Data Index: 1547431 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0885. Min Act: -0.1699

Data Index: 1594000 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.1028. Min Act: -0.1700

Data Index: 477038 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0873. Min Act: -0.1700

Data Index: 370262 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0948. Min Act: -0.1700

Data Index: 529587 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0975. Min Act: -0.1698

Data Index: 1387717 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0440. Min Act: -0.1700

Data Index: 1537214 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0451. Min Act: -0.1700

Data Index: 695277 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0615. Min Act: -0.1700

Data Index: 1580689 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0696. Min Act: -0.1700

Data Index: 1418375 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0763. Min Act: -0.1700

Data Index: 1629139 (Python Code)

Max Activating Token Index: 643

Text #19

Max Range: 4.2939. Min Range: -4.2939

Max Act: 4.0381. Min Act: -0.1699

Data Index: 236780 (C4 (Web Text))

Max Activating Token Index: 801