Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2046 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.6059. Min Act: -0.1700
Data Index: 1624565 (Python Code)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5576. Min Act: -0.1700
Data Index: 1487553 (Python Code)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5414. Min Act: -0.1700
Data Index: 1422601 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5414. Min Act: -0.1700
Data Index: 1376119 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5091. Min Act: -0.1700
Data Index: 1611227 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5253. Min Act: -0.1700
Data Index: 1635926 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5414. Min Act: -0.1700
Data Index: 1430895 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5091. Min Act: -0.1700
Data Index: 1569011 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4929. Min Act: -0.1700
Data Index: 1495431 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.5091. Min Act: -0.1700
Data Index: 1583384 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1653642 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1409419 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1492085 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1366294 (Python Code)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4605. Min Act: -0.1700
Data Index: 1639508 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1386396 (Python Code)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4929. Min Act: -0.1700
Data Index: 1550634 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4767. Min Act: -0.1700
Data Index: 1584809 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4442. Min Act: -0.1700
Data Index: 1371015 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6059. Min Range: -2.6059
Max Act: 2.4605. Min Act: -0.1700
Data Index: 1447508 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19