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

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

Neuron 258 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: 3.7538. Min Range: -3.7538

Max Act: 3.6191. Min Act: -0.1700

Data Index: 132854 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.7069. Min Act: -0.1700

Data Index: 513259 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.7538. Min Act: -0.1700

Data Index: 948499 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1521964 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6860. Min Act: -0.1700

Data Index: 1245128 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6917. Min Act: -0.1700

Data Index: 709519 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6537. Min Act: -0.1700

Data Index: 372747 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6841. Min Act: -0.1700

Data Index: 676475 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6221. Min Act: -0.1700

Data Index: 705290 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5802. Min Act: -0.1700

Data Index: 1427339 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5612. Min Act: -0.1700

Data Index: 1477171 (Python Code)

Max Activating Token Index: 957

Text #11

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5771. Min Act: -0.1700

Data Index: 246250 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6216. Min Act: -0.1700

Data Index: 219776 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5796. Min Act: -0.1700

Data Index: 239201 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5764. Min Act: -0.1700

Data Index: 665998 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5941. Min Act: -0.1700

Data Index: 1486186 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.6105. Min Act: -0.1700

Data Index: 520745 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5584. Min Act: -0.1700

Data Index: 695784 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5238. Min Act: -0.1700

Data Index: 642375 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.7538. Min Range: -3.7538

Max Act: 3.5096. Min Act: -0.1700

Data Index: 906541 (C4 (Web Text))

Max Activating Token Index: 101