Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 479 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.4751. Min Act: -0.1700

Data Index: 870780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.4124. Min Act: -0.1700

Data Index: 1123259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3967. Min Act: -0.1700

Data Index: 818536 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3967. Min Act: -0.1700

Data Index: 51745 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.4124. Min Act: -0.1700

Data Index: 887576 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3496. Min Act: -0.1699

Data Index: 21654 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3182. Min Act: -0.1700

Data Index: 59341 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3182. Min Act: -0.1700

Data Index: 915345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3339. Min Act: -0.1700

Data Index: 629874 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.3025. Min Act: -0.1700

Data Index: 725407 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2868. Min Act: -0.1700

Data Index: 613565 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2868. Min Act: -0.1700

Data Index: 100169 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2868. Min Act: -0.1700

Data Index: 998134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2711. Min Act: -0.1700

Data Index: 950431 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2711. Min Act: -0.1700

Data Index: 1131119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2554. Min Act: -0.1700

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2711. Min Act: -0.1700

Data Index: 1042460 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2554. Min Act: -0.1700

Data Index: 823265 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2554. Min Act: -0.1700

Data Index: 457025 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.4751. Min Range: -3.4751

Max Act: 3.2554. Min Act: -0.1700

Data Index: 682030 (C4 (Web Text))

Max Activating Token Index: 1023