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

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

Neuron 1533 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: 3.4033. Min Range: -3.4033

Max Act: 3.4033. Min Act: -0.1700

Data Index: 1498063 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.3874. Min Act: -0.1700

Data Index: 570301 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2933. Min Act: -0.1700

Data Index: 847564 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.3018. Min Act: -0.1700

Data Index: 706748 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2861. Min Act: -0.1700

Data Index: 286964 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1654883 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2947. Min Act: -0.1700

Data Index: 842915 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2607. Min Act: -0.1700

Data Index: 1631468 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2207. Min Act: -0.1700

Data Index: 1397247 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2152. Min Act: -0.1700

Data Index: 1472538 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1220273 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2060. Min Act: -0.1700

Data Index: 1609487 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2206. Min Act: -0.1700

Data Index: 445942 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2073. Min Act: -0.1700

Data Index: 3122 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1084746 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1432003 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2032. Min Act: -0.1700

Data Index: 257994 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.1904. Min Act: -0.1700

Data Index: 862255 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2077. Min Act: -0.1700

Data Index: 597344 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 3.4033. Min Range: -3.4033

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1208478 (C4 (Web Text))

Max Activating Token Index: 588