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

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

Neuron 1261 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: 3.7114. Min Range: -3.7114

Max Act: 3.7114. Min Act: -0.1695

Data Index: 1097860 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.6063. Min Act: -0.1700

Data Index: 964537 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.5570. Min Act: -0.1700

Data Index: 772157 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4634. Min Act: -0.1697

Data Index: 1029220 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1646601 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4270. Min Act: -0.1700

Data Index: 1231544 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4043. Min Act: -0.1700

Data Index: 1198468 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4214. Min Act: -0.1700

Data Index: 249343 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3958. Min Act: -0.1700

Data Index: 304230 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3791. Min Act: -0.1691

Data Index: 215730 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3799. Min Act: -0.1700

Data Index: 4053 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3247. Min Act: -0.1700

Data Index: 1593725 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3520. Min Act: -0.1696

Data Index: 1376523 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3501. Min Act: -0.1699

Data Index: 308575 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3471. Min Act: -0.1699

Data Index: 666298 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3239. Min Act: -0.1700

Data Index: 134446 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3200. Min Act: -0.1700

Data Index: 248555 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3336. Min Act: -0.1700

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1185984 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3066. Min Act: -0.1700

Data Index: 881081 (C4 (Web Text))

Max Activating Token Index: 108