Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1926 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.7312. Min Act: -0.1700

Data Index: 195329 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.5590. Min Act: -0.1700

Data Index: 824930 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.4493. Min Act: -0.1700

Data Index: 333466 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.4179. Min Act: -0.1700

Data Index: 56295 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.4023. Min Act: -0.1700

Data Index: 486743 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.4023. Min Act: -0.1700

Data Index: 1116313 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3866. Min Act: -0.1700

Data Index: 112813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3866. Min Act: -0.1700

Data Index: 858036 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3552. Min Act: -0.1700

Data Index: 147469 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3552. Min Act: -0.1700

Data Index: 182467 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3866. Min Act: -0.1700

Data Index: 209092 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3552. Min Act: -0.1700

Data Index: 1642780 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3395. Min Act: -0.1700

Data Index: 822235 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3395. Min Act: -0.1700

Data Index: 1058629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3238. Min Act: -0.1700

Data Index: 431527 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3238. Min Act: -0.1700

Data Index: 1299325 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3238. Min Act: -0.1700

Data Index: 1347867 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3395. Min Act: -0.1700

Data Index: 1495387 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3238. Min Act: -0.1700

Data Index: 66510 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.7312. Min Range: -3.7312

Max Act: 3.3238. Min Act: -0.1700

Data Index: 1027942 (C4 (Web Text))

Max Activating Token Index: 742