Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1632 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0388. Min Range: -4.0388
Max Act: 4.0388. Min Act: -0.1700
Data Index: 785549 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.8668. Min Act: -0.1700
Data Index: 568820 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.8199. Min Act: -0.1700
Data Index: 538654 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.8199. Min Act: -0.1700
Data Index: 853909 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7573. Min Act: -0.1700
Data Index: 616971 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7886. Min Act: -0.1700
Data Index: 965570 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7417. Min Act: -0.1700
Data Index: 591725 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7573. Min Act: -0.1700
Data Index: 138542 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7417. Min Act: -0.1700
Data Index: 1080879 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7573. Min Act: -0.1700
Data Index: 181210 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7573. Min Act: -0.1700
Data Index: 316302 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7573. Min Act: -0.1700
Data Index: 1029685 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.6947. Min Act: -0.1700
Data Index: 841809 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7260. Min Act: -0.1700
Data Index: 336534 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7260. Min Act: -0.1700
Data Index: 37726 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7417. Min Act: -0.1700
Data Index: 295381 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7104. Min Act: -0.1700
Data Index: 1229470 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7104. Min Act: -0.1700
Data Index: 1049554 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.7260. Min Act: -0.1700
Data Index: 932776 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0388. Min Range: -4.0388
Max Act: 3.6947. Min Act: -0.1700
Data Index: 1231210 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19