Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1902 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.0875. Min Act: -0.1700
Data Index: 470129 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.0717. Min Act: -0.1700
Data Index: 207212 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.1032. Min Act: -0.1700
Data Index: 927172 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.0243. Min Act: -0.1700
Data Index: 714508 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.0559. Min Act: -0.1700
Data Index: 552130 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1032. Min Range: -3.1032
Max Act: 3.0243. Min Act: -0.1700
Data Index: 1189355 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1224500 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9769. Min Act: -0.1700
Data Index: 102328 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1043173 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9452. Min Act: -0.1700
Data Index: 939764 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9136. Min Act: -0.1700
Data Index: 1214121 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9452. Min Act: -0.1700
Data Index: 17503 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9136. Min Act: -0.1700
Data Index: 449158 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9452. Min Act: -0.1700
Data Index: 800391 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.9136. Min Act: -0.1700
Data Index: 413357 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.8818. Min Act: -0.1700
Data Index: 811137 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.8977. Min Act: -0.1700
Data Index: 386588 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.8501. Min Act: -0.1700
Data Index: 46472 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.8659. Min Act: -0.1700
Data Index: 381604 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1032. Min Range: -3.1032
Max Act: 2.8659. Min Act: -0.1700
Data Index: 574253 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19