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

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

Neuron 495 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.1962. Min Act: -0.1700

Data Index: 997542 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0859. Min Act: -0.1700

Data Index: 732541 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0070. Min Act: -0.1700

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0544. Min Act: -0.1700

Data Index: 1341502 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0228. Min Act: -0.1700

Data Index: 1071672 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0070. Min Act: -0.1700

Data Index: 840678 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9754. Min Act: -0.1700

Data Index: 893943 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.1962. Min Range: -3.1962

Max Act: 3.0070. Min Act: -0.1700

Data Index: 648735 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9120. Min Act: -0.1700

Data Index: 325989 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9912. Min Act: -0.1700

Data Index: 762537 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9595. Min Act: -0.1700

Data Index: 157926 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9120. Min Act: -0.1700

Data Index: 693219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8644. Min Act: -0.1700

Data Index: 977486 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8803. Min Act: -0.1700

Data Index: 166109 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.9120. Min Act: -0.1700

Data Index: 785639 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8961. Min Act: -0.1700

Data Index: 1237742 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8326. Min Act: -0.1700

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8485. Min Act: -0.1700

Data Index: 154802 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.8008. Min Act: -0.1700

Data Index: 1236622 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 3.1962. Min Range: -3.1962

Max Act: 2.7689. Min Act: -0.1700

Data Index: 801027 (C4 (Web Text))

Max Activating Token Index: 643