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

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

Neuron 1064 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: 7.5070. Min Range: -7.5070

Max Act: 7.5070. Min Act: -0.1700

Data Index: 269512 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2883. Min Act: -0.1700

Data Index: 1036207 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.3195. Min Act: -0.1700

Data Index: 411870 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.3508. Min Act: -0.1700

Data Index: 1102102 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2570. Min Act: -0.1700

Data Index: 12766 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2258. Min Act: -0.1700

Data Index: 1100416 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2570. Min Act: -0.1700

Data Index: 831788 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2570. Min Act: -0.1700

Data Index: 993667 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1945. Min Act: -0.1700

Data Index: 1036238 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1945. Min Act: -0.1700

Data Index: 192381 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1945. Min Act: -0.1700

Data Index: 289122 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1945. Min Act: -0.1700

Data Index: 860116 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.2258. Min Act: -0.1700

Data Index: 486205 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1633. Min Act: -0.1700

Data Index: 939197 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1320. Min Act: -0.1700

Data Index: 405132 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1945. Min Act: -0.1700

Data Index: 17469 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.1320. Min Act: -0.1700

Data Index: 610323 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 7.5070. Min Range: -7.5070

Max Act: 7.0383. Min Act: -0.1700

Data Index: 95168 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 7.5070. Min Range: -7.5070

Max Act: 6.9758. Min Act: -0.1700

Data Index: 1112315 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 7.5070. Min Range: -7.5070

Max Act: 6.9133. Min Act: -0.1700

Data Index: 775254 (C4 (Web Text))

Max Activating Token Index: 650