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

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

Neuron 861 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: 3.9553. Min Range: -3.9553

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1511448 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.9454. Min Act: -0.1700

Data Index: 1632186 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1364502 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.9163. Min Act: -0.1700

Data Index: 1598095 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8809. Min Act: -0.1700

Data Index: 1647226 (Python Code)

Max Activating Token Index: 684

Text #5

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8730. Min Act: -0.1700

Data Index: 1474310 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8580. Min Act: -0.1700

Data Index: 1584229 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1421913 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8273. Min Act: -0.1700

Data Index: 1576137 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8305. Min Act: -0.1700

Data Index: 1541573 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8430. Min Act: -0.1700

Data Index: 1586942 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8331. Min Act: -0.1700

Data Index: 1470428 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7967. Min Act: -0.1700

Data Index: 1480317 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7985. Min Act: -0.1700

Data Index: 1548825 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8033. Min Act: -0.1700

Data Index: 1377438 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.8182. Min Act: -0.1700

Data Index: 1595279 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1408422 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7931. Min Act: -0.1700

Data Index: 213793 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7792. Min Act: -0.1700

Data Index: 1386486 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 3.9553. Min Range: -3.9553

Max Act: 3.7709. Min Act: -0.1700

Data Index: 1522068 (Python Code)

Max Activating Token Index: 757