Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1105 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0900. Min Act: -0.1700
Data Index: 804426 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 735442 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9650. Min Act: -0.1700
Data Index: 699372 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9650. Min Act: -0.1700
Data Index: 1295833 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9650. Min Act: -0.1700
Data Index: 1107551 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9337. Min Act: -0.1700
Data Index: 301624 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9337. Min Act: -0.1700
Data Index: 556397 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9337. Min Act: -0.1700
Data Index: 1277443 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9024. Min Act: -0.1700
Data Index: 680105 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9024. Min Act: -0.1700
Data Index: 734723 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 863055 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 1086079 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 91975 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 239968 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 298017 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 515053 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8711. Min Act: -0.1700
Data Index: 901246 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8399. Min Act: -0.1700
Data Index: 982693 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8086. Min Act: -0.1700
Data Index: 1011754 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.8399. Min Act: -0.1700
Data Index: 392169 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19