Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.2665. Min Act: -0.1700
Data Index: 2109642 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1727. Min Act: -0.1700
Data Index: 2067431 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1727. Min Act: -0.1700
Data Index: 7761967 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 5908541 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1415. Min Act: -0.1700
Data Index: 4251138 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1415. Min Act: -0.1700
Data Index: 7995632 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6016020 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 3384083 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1415. Min Act: -0.1700
Data Index: 4864569 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 4449144 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 8182347 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 2307360 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 7546909 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 2061990 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 7068197 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6725726 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.0790. Min Act: -0.1700
Data Index: 2396352 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.0790. Min Act: -0.1700
Data Index: 2499860 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.0790. Min Act: -0.1700
Data Index: 5241390 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2665. Min Range: -5.2665
Max Act: 5.1102. Min Act: -0.1700
Data Index: 5893280 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19