Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 295 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.1963. Min Act: -0.1700
Data Index: 444800 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.1025. Min Act: -0.1700
Data Index: 7539564 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.0713. Min Act: -0.1700
Data Index: 6498816 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.0400. Min Act: -0.1700
Data Index: 162709 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.0400. Min Act: -0.1700
Data Index: 869062 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.0088. Min Act: -0.1700
Data Index: 2846756 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1963. Min Range: -6.1963
Max Act: 6.0088. Min Act: -0.1700
Data Index: 7141190 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9775. Min Act: -0.1700
Data Index: 170326 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9150. Min Act: -0.1700
Data Index: 2932364 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9150. Min Act: -0.1700
Data Index: 4580623 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 8193788 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9150. Min Act: -0.1700
Data Index: 3522090 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 7708022 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9150. Min Act: -0.1700
Data Index: 4164240 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9150. Min Act: -0.1700
Data Index: 8621234 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.9463. Min Act: -0.1700
Data Index: 873713 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 4599077 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 7749325 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 3535429 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1963. Min Range: -6.1963
Max Act: 5.8213. Min Act: -0.1700
Data Index: 3611752 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19