Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1543 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4863. Min Act: -0.1700
Data Index: 1416846 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4539. Min Act: -0.1700
Data Index: 684478 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4701. Min Act: -0.1700
Data Index: 1630137 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4376. Min Act: -0.1700
Data Index: 119428 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1551261 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1616073 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4213. Min Act: -0.1700
Data Index: 1416630 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4213. Min Act: -0.1700
Data Index: 1611088 (Python Code)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3887. Min Act: -0.1700
Data Index: 1371781 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.4051. Min Act: -0.1700
Data Index: 1434266 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3887. Min Act: -0.1700
Data Index: 1511660 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3887. Min Act: -0.1700
Data Index: 1432460 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3887. Min Act: -0.1700
Data Index: 1578850 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1069764 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1533074 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1385290 (Python Code)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1543796 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1506955 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3560. Min Act: -0.1700
Data Index: 1508403 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4863. Min Range: -2.4863
Max Act: 2.3397. Min Act: -0.1700
Data Index: 1429262 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19