Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 525 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1933. Min Range: -5.1933
Max Act: 5.1933. Min Act: -0.1700
Data Index: 672333 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1933. Min Range: -5.1933
Max Act: 5.0995. Min Act: -0.1700
Data Index: 662744 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1933. Min Range: -5.1933
Max Act: 5.0370. Min Act: -0.1700
Data Index: 1006005 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1933. Min Range: -5.1933
Max Act: 5.0683. Min Act: -0.1700
Data Index: 557107 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1933. Min Range: -5.1933
Max Act: 5.0058. Min Act: -0.1700
Data Index: 1104595 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9120. Min Act: -0.1700
Data Index: 1349927 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9433. Min Act: -0.1700
Data Index: 428596 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9745. Min Act: -0.1700
Data Index: 346152 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9433. Min Act: -0.1700
Data Index: 141691 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9745. Min Act: -0.1700
Data Index: 257747 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9433. Min Act: -0.1700
Data Index: 40373 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.9433. Min Act: -0.1700
Data Index: 113792 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.8808. Min Act: -0.1700
Data Index: 423811 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.8808. Min Act: -0.1700
Data Index: 1091412 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.8495. Min Act: -0.1700
Data Index: 430932 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.8183. Min Act: -0.1700
Data Index: 865410 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.8495. Min Act: -0.1700
Data Index: 529398 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.7870. Min Act: -0.1700
Data Index: 311109 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.7870. Min Act: -0.1700
Data Index: 935608 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1933. Min Range: -5.1933
Max Act: 4.7870. Min Act: -0.1700
Data Index: 190842 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19