Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 229 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.4946. Min Act: -0.1700

Data Index: 61782 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.4005. Min Act: -0.1700

Data Index: 243905 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.4319. Min Act: -0.1700

Data Index: 981496 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.4005. Min Act: -0.1700

Data Index: 37638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.4005. Min Act: -0.1700

Data Index: 988459 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.3063. Min Act: -0.1700

Data Index: 138430 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2749. Min Act: -0.1700

Data Index: 758803 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2749. Min Act: -0.1700

Data Index: 911425 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2435. Min Act: -0.1700

Data Index: 1332587 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2749. Min Act: -0.1700

Data Index: 259481 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2592. Min Act: -0.1700

Data Index: 402453 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2592. Min Act: -0.1700

Data Index: 1187202 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2278. Min Act: -0.1700

Data Index: 732863 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2435. Min Act: -0.1700

Data Index: 583937 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.1963. Min Act: -0.1700

Data Index: 414457 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2278. Min Act: -0.1700

Data Index: 525868 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2278. Min Act: -0.1700

Data Index: 319750 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2120. Min Act: -0.1700

Data Index: 204731 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.1963. Min Act: -0.1700

Data Index: 52662 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 3.4946. Min Range: -3.4946

Max Act: 3.2120. Min Act: -0.1700

Data Index: 847216 (C4 (Web Text))

Max Activating Token Index: 274