Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.3081. Min Act: -0.1700
Data Index: 4124640 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.3081. Min Act: -0.1700
Data Index: 8339446 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.2456. Min Act: -0.1700
Data Index: 177635 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.1518. Min Act: -0.1700
Data Index: 97604 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.1518. Min Act: -0.1700
Data Index: 7043399 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.0581. Min Act: -0.1700
Data Index: 3753833 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.0581. Min Act: -0.1700
Data Index: 746691 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.0581. Min Act: -0.1700
Data Index: 3170829 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.0581. Min Act: -0.1700
Data Index: 729240 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3081. Min Range: -5.3081
Max Act: 5.0268. Min Act: -0.1700
Data Index: 905659 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9956. Min Act: -0.1700
Data Index: 7067787 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9643. Min Act: -0.1700
Data Index: 4385615 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9643. Min Act: -0.1700
Data Index: 734972 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9956. Min Act: -0.1700
Data Index: 8411887 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9643. Min Act: -0.1700
Data Index: 5853442 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9643. Min Act: -0.1700
Data Index: 2192818 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9643. Min Act: -0.1700
Data Index: 1955875 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9331. Min Act: -0.1700
Data Index: 7313447 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9331. Min Act: -0.1700
Data Index: 587426 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3081. Min Range: -5.3081
Max Act: 4.9018. Min Act: -0.1700
Data Index: 2836372 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19