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

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

Neuron 1394 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: 3.4324. Min Range: -3.4324

Max Act: 3.4324. Min Act: -0.1700

Data Index: 888402 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3778. Min Act: -0.1700

Data Index: 432298 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2838. Min Act: -0.1700

Data Index: 1378154 (Python Code)

Max Activating Token Index: 764

Text #3

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2777. Min Act: -0.1700

Data Index: 661500 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2608. Min Act: -0.1700

Data Index: 317799 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2305. Min Act: -0.1700

Data Index: 150148 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2121. Min Act: -0.1700

Data Index: 674958 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2034. Min Act: -0.1700

Data Index: 890174 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1317689 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2107. Min Act: -0.1700

Data Index: 918342 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1810. Min Act: -0.1700

Data Index: 173541 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1701. Min Act: -0.1700

Data Index: 930149 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1816. Min Act: -0.1700

Data Index: 264841 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1784. Min Act: -0.1700

Data Index: 117264 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1234255 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1787. Min Act: -0.1700

Data Index: 679125 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1582. Min Act: -0.1700

Data Index: 896324 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1469. Min Act: -0.1700

Data Index: 1499415 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1407. Min Act: -0.1700

Data Index: 1616754 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.1430. Min Act: -0.1700

Data Index: 922529 (C4 (Web Text))

Max Activating Token Index: 824