Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 592 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.4564. Min Act: -0.1700
Data Index: 965178 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.4251. Min Act: -0.1700
Data Index: 217768 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.4564. Min Act: -0.1700
Data Index: 1219240 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.4251. Min Act: -0.1700
Data Index: 1150981 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.3626. Min Act: -0.1700
Data Index: 879207 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.3001. Min Act: -0.1700
Data Index: 387844 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.3314. Min Act: -0.1700
Data Index: 1345208 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.3001. Min Act: -0.1700
Data Index: 1156487 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2376. Min Act: -0.1700
Data Index: 1099746 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2376. Min Act: -0.1700
Data Index: 493955 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2688. Min Act: -0.1700
Data Index: 422405 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.3001. Min Act: -0.1700
Data Index: 1191508 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2376. Min Act: -0.1700
Data Index: 1125363 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2688. Min Act: -0.1700
Data Index: 198238 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2063. Min Act: -0.1700
Data Index: 411545 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2063. Min Act: -0.1700
Data Index: 498731 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.1751. Min Act: -0.1700
Data Index: 702342 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.2063. Min Act: -0.1700
Data Index: 898527 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.1751. Min Act: -0.1700
Data Index: 1299626 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4564. Min Range: -4.4564
Max Act: 4.1438. Min Act: -0.1700
Data Index: 1280868 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19