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

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

Neuron 1441 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: 3.9824. Min Range: -3.9824

Max Act: 3.9824. Min Act: -0.1700

Data Index: 1248435 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.9445. Min Act: -0.1700

Data Index: 887025 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.8589. Min Act: -0.1700

Data Index: 824505 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1550681 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.8154. Min Act: -0.1700

Data Index: 390115 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7965. Min Act: -0.1700

Data Index: 142942 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7997. Min Act: -0.1700

Data Index: 1413063 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7489. Min Act: -0.1700

Data Index: 924960 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7738. Min Act: -0.1700

Data Index: 1583234 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7404. Min Act: -0.1700

Data Index: 1398815 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7299. Min Act: -0.1700

Data Index: 1070403 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7424. Min Act: -0.1700

Data Index: 1385597 (Python Code)

Max Activating Token Index: 761

Text #12

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1447278 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7300. Min Act: -0.1700

Data Index: 1556533 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7388. Min Act: -0.1700

Data Index: 801734 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7200. Min Act: -0.1700

Data Index: 759934 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1508497 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.7110. Min Act: -0.1700

Data Index: 835450 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.6790. Min Act: -0.1700

Data Index: 886127 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 3.9824. Min Range: -3.9824

Max Act: 3.6450. Min Act: -0.1700

Data Index: 642547 (C4 (Web Text))

Max Activating Token Index: 954