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

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

Neuron 820 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: 3.4770. Min Range: -3.4770

Max Act: 3.4770. Min Act: -0.1700

Data Index: 1462244 (Python Code)

Max Activating Token Index: 310

Text #1

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.4114. Min Act: -0.1700

Data Index: 1656044 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3991. Min Act: -0.1700

Data Index: 1146358 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1493925 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3925. Min Act: -0.1700

Data Index: 1072669 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3988. Min Act: -0.1700

Data Index: 183257 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3750. Min Act: -0.1700

Data Index: 770346 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3697. Min Act: -0.1700

Data Index: 521911 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3808. Min Act: -0.1700

Data Index: 13184 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3408. Min Act: -0.1700

Data Index: 1539076 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3418. Min Act: -0.1700

Data Index: 185412 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3190. Min Act: -0.1700

Data Index: 478750 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3197. Min Act: -0.1700

Data Index: 292495 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3312. Min Act: -0.1700

Data Index: 1191063 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3148. Min Act: -0.1700

Data Index: 791531 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.2984. Min Act: -0.1700

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3124. Min Act: -0.1700

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.2964. Min Act: -0.1700

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.3025. Min Act: -0.1700

Data Index: 920357 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 3.4770. Min Range: -3.4770

Max Act: 3.2984. Min Act: -0.1700

Data Index: 1474451 (Python Code)

Max Activating Token Index: 702