Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.2428. Min Act: -0.1700
Data Index: 7213125 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1930. Min Act: -0.1700
Data Index: 261519 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1930. Min Act: -0.1700
Data Index: 1653174 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1764. Min Act: -0.1700
Data Index: 1560004 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1097. Min Act: -0.1700
Data Index: 6887673 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1097. Min Act: -0.1700
Data Index: 3846350 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1097. Min Act: -0.1700
Data Index: 4719764 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0930. Min Act: -0.1700
Data Index: 5909015 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0930. Min Act: -0.1700
Data Index: 2317261 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0762. Min Act: -0.1700
Data Index: 1232515 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0594. Min Act: -0.1700
Data Index: 4751085 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0594. Min Act: -0.1700
Data Index: 6676493 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0762. Min Act: -0.1700
Data Index: 2575924 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0930. Min Act: -0.1700
Data Index: 1112004 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0594. Min Act: -0.1700
Data Index: 8785487 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.1097. Min Act: -0.1700
Data Index: 6172026 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0930. Min Act: -0.1700
Data Index: 7647837 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0426. Min Act: -0.1700
Data Index: 1386417 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0594. Min Act: -0.1700
Data Index: 4911748 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2428. Min Range: -2.2428
Max Act: 2.0594. Min Act: -0.1700
Data Index: 4490751 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19