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

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

Neuron 1399 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.3364. Min Act: -0.1700

Data Index: 1128103 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.2739. Min Act: -0.1700

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.1489. Min Act: -0.1700

Data Index: 46764 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.1177. Min Act: -0.1700

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.1802. Min Act: -0.1700

Data Index: 700663 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.1802. Min Act: -0.1700

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.1177. Min Act: -0.1700

Data Index: 374551 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.0239. Min Act: -0.1700

Data Index: 962645 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 5.3364. Min Range: -5.3364

Max Act: 5.0552. Min Act: -0.1700

Data Index: 614319 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9927. Min Act: -0.1700

Data Index: 547487 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9614. Min Act: -0.1700

Data Index: 1042224 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9302. Min Act: -0.1700

Data Index: 819604 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9614. Min Act: -0.1700

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.8677. Min Act: -0.1700

Data Index: 472724 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9302. Min Act: -0.1700

Data Index: 323080 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9302. Min Act: -0.1700

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.8989. Min Act: -0.1700

Data Index: 116565 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.8677. Min Act: -0.1700

Data Index: 1157236 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.8989. Min Act: -0.1700

Data Index: 512548 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 5.3364. Min Range: -5.3364

Max Act: 4.9614. Min Act: -0.1700

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 581