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

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

Neuron 1829 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: 4.1159. Min Range: -4.1159

Max Act: 4.1159. Min Act: -0.1700

Data Index: 279141 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 4.1159. Min Range: -4.1159

Max Act: 4.0613. Min Act: -0.1700

Data Index: 500561 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 4.1159. Min Range: -4.1159

Max Act: 4.0104. Min Act: -0.1700

Data Index: 350803 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9540. Min Act: -0.1700

Data Index: 477910 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9299. Min Act: -0.1700

Data Index: 201231 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9480. Min Act: -0.1700

Data Index: 979318 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9575. Min Act: -0.1700

Data Index: 237444 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9546. Min Act: -0.1700

Data Index: 1237471 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9464. Min Act: -0.1700

Data Index: 418708 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9193. Min Act: -0.1700

Data Index: 1052513 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9437. Min Act: -0.1700

Data Index: 1312330 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8787. Min Act: -0.1700

Data Index: 13513 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9034. Min Act: -0.1700

Data Index: 380076 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8920. Min Act: -0.1700

Data Index: 1367919 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8990. Min Act: -0.1700

Data Index: 1550247 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8937. Min Act: -0.1700

Data Index: 355741 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.9164. Min Act: -0.1700

Data Index: 1284895 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8879. Min Act: -0.1700

Data Index: 696527 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8921. Min Act: -0.1700

Data Index: 1086229 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 4.1159. Min Range: -4.1159

Max Act: 3.8716. Min Act: -0.1700

Data Index: 47586 (C4 (Web Text))

Max Activating Token Index: 903