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

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

Neuron 149 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: 2.9980. Min Range: -2.9980

Max Act: 2.9980. Min Act: -0.1668

Data Index: 367396 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.8626. Min Act: -0.1700

Data Index: 981901 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.8683. Min Act: -0.1700

Data Index: 638538 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.8500. Min Act: -0.1700

Data Index: 1465126 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.8418. Min Act: -0.1700

Data Index: 802602 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.8074. Min Act: -0.1698

Data Index: 967707 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7809. Min Act: -0.1700

Data Index: 1282235 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7833. Min Act: -0.1700

Data Index: 920547 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7737. Min Act: -0.1700

Data Index: 1065251 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7681. Min Act: -0.1700

Data Index: 720534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7576. Min Act: -0.1700

Data Index: 418993 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7172. Min Act: -0.1700

Data Index: 1646071 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7155. Min Act: -0.1700

Data Index: 895541 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7190. Min Act: -0.1586

Data Index: 341697 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7014. Min Act: -0.1700

Data Index: 1144094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7127. Min Act: -0.1700

Data Index: 1096622 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7003. Min Act: -0.1687

Data Index: 1046653 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.7044. Min Act: -0.1700

Data Index: 175546 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.6975. Min Act: -0.1571

Data Index: 288381 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 2.9980. Min Range: -2.9980

Max Act: 2.6992. Min Act: -0.1698

Data Index: 278679 (C4 (Web Text))

Max Activating Token Index: 375