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

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

Neuron 1135 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: 3.2278. Min Range: -3.2278

Max Act: 3.2278. Min Act: -0.1700

Data Index: 717716 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.2116. Min Act: -0.1697

Data Index: 1603509 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.1933. Min Act: -0.1700

Data Index: 146541 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.1081. Min Act: -0.1694

Data Index: 1472225 (Python Code)

Max Activating Token Index: 600

Text #4

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0922. Min Act: -0.1700

Data Index: 995354 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0461. Min Act: -0.1699

Data Index: 1206953 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0303. Min Act: -0.1699

Data Index: 1419816 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0435. Min Act: -0.1700

Data Index: 1516986 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0390. Min Act: -0.1700

Data Index: 1610254 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0341. Min Act: -0.1700

Data Index: 1580739 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 3.2278. Min Range: -3.2278

Max Act: 3.0226. Min Act: -0.1700

Data Index: 919479 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1588659 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9599. Min Act: -0.1699

Data Index: 1060236 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9497. Min Act: -0.1700

Data Index: 1437158 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9526. Min Act: -0.1700

Data Index: 1452960 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9542. Min Act: -0.1699

Data Index: 910135 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9555. Min Act: -0.1700

Data Index: 615883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9359. Min Act: -0.1700

Data Index: 1142748 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.9362. Min Act: -0.1697

Data Index: 1401802 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 3.2278. Min Range: -3.2278

Max Act: 2.8983. Min Act: -0.1700

Data Index: 1613101 (Python Code)

Max Activating Token Index: 326