Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 203 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.5183. Min Act: -0.1700
Data Index: 216777 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4859. Min Act: -0.1700
Data Index: 1282724 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4697. Min Act: -0.1700
Data Index: 1315602 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4697. Min Act: -0.1700
Data Index: 906237 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4209. Min Act: -0.1700
Data Index: 123235 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4209. Min Act: -0.1700
Data Index: 1277038 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4209. Min Act: -0.1700
Data Index: 711511 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.4372. Min Act: -0.1700
Data Index: 521317 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3883. Min Act: -0.1700
Data Index: 374495 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 1639129 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 1182187 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3883. Min Act: -0.1700
Data Index: 1282397 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 846086 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 274650 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3883. Min Act: -0.1700
Data Index: 471432 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 39485 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3556. Min Act: -0.1700
Data Index: 1238672 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3556. Min Act: -0.1700
Data Index: 872119 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3720. Min Act: -0.1700
Data Index: 780656 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5183. Min Range: -2.5183
Max Act: 2.3556. Min Act: -0.1700
Data Index: 476817 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19