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

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

Neuron 1727 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: 3.4450. Min Range: -3.4450

Max Act: 3.4450. Min Act: -0.1700

Data Index: 1033442 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4322. Min Act: -0.1700

Data Index: 572359 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4025. Min Act: -0.1700

Data Index: 271735 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4192. Min Act: -0.1700

Data Index: 281106 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3722. Min Act: -0.1700

Data Index: 1193845 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3341. Min Act: -0.1700

Data Index: 965411 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.2933. Min Act: -0.1700

Data Index: 144776 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3140. Min Act: -0.1700

Data Index: 347367 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.2711. Min Act: -0.1700

Data Index: 361203 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.2693. Min Act: -0.1700

Data Index: 245911 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.2113. Min Act: -0.1700

Data Index: 778175 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.2202. Min Act: -0.1700

Data Index: 503515 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1876. Min Act: -0.1700

Data Index: 403943 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1156. Min Act: -0.1700

Data Index: 42078 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1748. Min Act: -0.1700

Data Index: 1279302 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1295. Min Act: -0.1700

Data Index: 742826 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1078. Min Act: -0.1700

Data Index: 951043 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1158. Min Act: -0.1700

Data Index: 688665 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1351022 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1351938 (C4 (Web Text))

Max Activating Token Index: 653