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

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

Neuron 1043 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: 3.5099. Min Range: -3.5099

Max Act: 3.4944. Min Act: -0.1696

Data Index: 747638 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.5099. Min Act: -0.1700

Data Index: 1349852 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.4728. Min Act: -0.1700

Data Index: 543499 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.4450. Min Act: -0.1590

Data Index: 375066 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.4646. Min Act: -0.1500

Data Index: 656988 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.4215. Min Act: -0.1695

Data Index: 581219 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3924. Min Act: -0.1695

Data Index: 571001 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3716. Min Act: -0.1644

Data Index: 306464 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3770. Min Act: -0.1700

Data Index: 1185341 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3713. Min Act: -0.1700

Data Index: 764453 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3538. Min Act: -0.1696

Data Index: 545476 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3666. Min Act: -0.1700

Data Index: 510466 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3123. Min Act: -0.1700

Data Index: 1389285 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3311. Min Act: -0.1665

Data Index: 1079368 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3064. Min Act: -0.1679

Data Index: 516177 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.3281. Min Act: -0.1700

Data Index: 867448 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.2872. Min Act: -0.1696

Data Index: 326055 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.2945. Min Act: -0.1700

Data Index: 208922 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.2918. Min Act: -0.1699

Data Index: 1017057 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 3.5099. Min Range: -3.5099

Max Act: 3.2928. Min Act: -0.1700

Data Index: 301967 (C4 (Web Text))

Max Activating Token Index: 421