Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0924. Min Range: -4.0924
Max Act: 4.0924. Min Act: -0.1700
Data Index: 7018703 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0924. Min Range: -4.0924
Max Act: 4.0611. Min Act: -0.1700
Data Index: 8575272 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 3696784 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9986. Min Act: -0.1700
Data Index: 4393354 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 6032229 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8110. Min Act: -0.1700
Data Index: 8026639 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 8605838 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 2989124 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 4414376 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 2781942 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 7200642 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8736. Min Act: -0.1700
Data Index: 1478588 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 4045911 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 3416459 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 2367112 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8736. Min Act: -0.1700
Data Index: 1002064 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8736. Min Act: -0.1700
Data Index: 6879118 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 6604607 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.9048. Min Act: -0.1700
Data Index: 6202843 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0924. Min Range: -4.0924
Max Act: 3.8423. Min Act: -0.1700
Data Index: 813454 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19