Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 603 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3361. Min Act: -0.1700
Data Index: 4052310 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 2243979 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 3979909 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 6648236 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 22119 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 7510328 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2111. Min Act: -0.1700
Data Index: 6149286 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2424. Min Act: -0.1700
Data Index: 6168760 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2736. Min Act: -0.1700
Data Index: 1621476 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2111. Min Act: -0.1700
Data Index: 1265968 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3361. Min Act: -0.1700
Data Index: 2572723 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2111. Min Act: -0.1700
Data Index: 4142331 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2111. Min Act: -0.1700
Data Index: 5610977 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2111. Min Act: -0.1700
Data Index: 5488451 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2424. Min Act: -0.1700
Data Index: 1824299 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.3049. Min Act: -0.1700
Data Index: 1430040 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2424. Min Act: -0.1700
Data Index: 6181292 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.2424. Min Act: -0.1700
Data Index: 3474329 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.1799. Min Act: -0.1700
Data Index: 2683951 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3986. Min Range: -4.3986
Max Act: 4.1799. Min Act: -0.1700
Data Index: 6102955 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19