Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.5665. Min Act: -0.1700
Data Index: 5675302 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1075053 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.3790. Min Act: -0.1700
Data Index: 5008699 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1915. Min Act: -0.1700
Data Index: 3103568 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1603. Min Act: -0.1700
Data Index: 7416563 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1915. Min Act: -0.1700
Data Index: 684154 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1603. Min Act: -0.1700
Data Index: 1068325 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1603. Min Act: -0.1700
Data Index: 1176177 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1603. Min Act: -0.1700
Data Index: 3717668 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0978. Min Act: -0.1700
Data Index: 7157483 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8275228 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.1290. Min Act: -0.1700
Data Index: 6349431 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0978. Min Act: -0.1700
Data Index: 5672259 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0665. Min Act: -0.1700
Data Index: 247802 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0353. Min Act: -0.1700
Data Index: 8783925 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0353. Min Act: -0.1700
Data Index: 3546654 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0353. Min Act: -0.1700
Data Index: 6912356 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0040. Min Act: -0.1700
Data Index: 7401991 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0665. Min Act: -0.1700
Data Index: 4104635 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5665. Min Range: -5.5665
Max Act: 5.0040. Min Act: -0.1700
Data Index: 4489244 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19