Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.8654. Min Act: -0.1700
Data Index: 2281508 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.8018. Min Act: -0.1700
Data Index: 2999134 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7699. Min Act: -0.1700
Data Index: 915501 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7699. Min Act: -0.1700
Data Index: 3813936 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7699. Min Act: -0.1700
Data Index: 4650970 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7540. Min Act: -0.1700
Data Index: 5756401 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.8018. Min Act: -0.1700
Data Index: 5476524 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7220. Min Act: -0.1700
Data Index: 3147326 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 5648405 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 797835 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.6740. Min Act: -0.1700
Data Index: 1147360 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 1219476 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 3952461 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.6900. Min Act: -0.1700
Data Index: 3024047 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 1122633 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 2638387 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.7060. Min Act: -0.1700
Data Index: 175579 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.6900. Min Act: -0.1700
Data Index: 7626555 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.6900. Min Act: -0.1700
Data Index: 8405560 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8654. Min Range: -2.8654
Max Act: 2.6419. Min Act: -0.1700
Data Index: 1396531 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19