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

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

Neuron 1125 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: 3.2156. Min Range: -3.2156

Max Act: 3.2156. Min Act: -0.1700

Data Index: 74741 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.1294. Min Act: -0.1700

Data Index: 929104 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.1160. Min Act: -0.1700

Data Index: 901373 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.1150. Min Act: -0.1699

Data Index: 1021282 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.1018. Min Act: -0.1700

Data Index: 454377 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0796. Min Act: -0.1700

Data Index: 523876 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0411. Min Act: -0.1700

Data Index: 658335 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0534. Min Act: -0.1700

Data Index: 476367 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1267673 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0345. Min Act: -0.1700

Data Index: 303166 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1095469 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0168. Min Act: -0.1700

Data Index: 289132 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0146. Min Act: -0.1700

Data Index: 895021 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0006. Min Act: -0.1700

Data Index: 158529 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 3.2156. Min Range: -3.2156

Max Act: 2.9994. Min Act: -0.1700

Data Index: 25840 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 3.2156. Min Range: -3.2156

Max Act: 2.9837. Min Act: -0.1700

Data Index: 1243093 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 3.2156. Min Range: -3.2156

Max Act: 3.0039. Min Act: -0.1700

Data Index: 1008417 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.2156. Min Range: -3.2156

Max Act: 2.9983. Min Act: -0.1700

Data Index: 20598 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 3.2156. Min Range: -3.2156

Max Act: 2.9947. Min Act: -0.1700

Data Index: 19400 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 3.2156. Min Range: -3.2156

Max Act: 2.9988. Min Act: -0.1699

Data Index: 651172 (C4 (Web Text))

Max Activating Token Index: 392