Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 761 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.7775. Min Act: -0.1700
Data Index: 4135444 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.7150. Min Act: -0.1700
Data Index: 6529626 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6837. Min Act: -0.1700
Data Index: 6240043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6141677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 1518587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6529391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 3013418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 7750233 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 2420892 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 7264053 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6802679 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 1066195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 4866403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 8342115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 1230829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 8157740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 3383864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 7948980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6525. Min Act: -0.1700
Data Index: 7754519 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7775. Min Range: -4.7775
Max Act: 4.6212. Min Act: -0.1700
Data Index: 1450789 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19